CN109981753A - A kind of system and resource allocation methods of the edge calculations of the software definition of internet of things oriented - Google Patents
A kind of system and resource allocation methods of the edge calculations of the software definition of internet of things oriented Download PDFInfo
- Publication number
- CN109981753A CN109981753A CN201910172114.7A CN201910172114A CN109981753A CN 109981753 A CN109981753 A CN 109981753A CN 201910172114 A CN201910172114 A CN 201910172114A CN 109981753 A CN109981753 A CN 109981753A
- Authority
- CN
- China
- Prior art keywords
- internet
- terminal user
- things
- task
- things terminal
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/64—Routing or path finding of packets in data switching networks using an overlay routing layer
-
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of system of the edge calculations of the software definition of internet of things oriented and resource allocation methods, including the multiple access base station equipment in honeycomb deployment, has the fringe node EN of data processing and computing function in the deployment of each base station, while EN is connected to centralized computing resource pool by high speed fibre.The theory of software defined network and network function virtualization, mask data level and control plane are introduced, network function is decoupled from hardware device.Centralized control is realized using OpenFlow controller, executes mobile management, data processing upwardly through programmable application programming interfaces, resource allocation function passes downwardly through OpenFlow interface and communicates with transponder, realizes the forwarding of user data.Consider the different characteristics of internet-of-things terminal user, it will be in the assigning process of Si Tankeer Burger game applications to internet-of-things terminal user's computing resource, under the premise of ensureing QoS of customer, resource utilization is improved to the maximum extent, meets the needs of more different type users.
Description
Technical field
The present invention relates to field of cloud calculation, in particular to a kind of system of the edge calculations of the software definition of internet of things oriented
And resource allocation methods.
Background technique
Internet of Things is the important component of generation information technology and the important development stage of information age.Its
By Intellisense, identification technology and general fit calculation etc. communicate cognition technology, are widely used in the fusion of network, push simultaneously
Smart home, wisdom traffic, electron medical treatment, smart city, the development of industrial automation.
The core technology of Internet of Things first is that cloud computing, cloud computing is the increase of related service Internet-based, uses
And delivery mode, it is usually directed to through internet and the resource of dynamic easily extension and often virtualization is provided.Internet of Things at present
Server disposition beyond the clouds, pass through cloud computing provide application layer respective services.
But with the gradually development of internet of things service, sensing data amount increase sharply and wisdom traffic, electronics doctor
The development of the low latencies, high reliability business such as treatment, challenges to traditional Internet of Things framework based on cloud computing: first, big
The sensing data of amount uploads to cloud via backbone network, occupies a large amount of bandwidth resources, meets with sudden flow growth and easily causes
Network congestion；Second, propagation delay time is higher, the requirement of low time delay business cannot be coped with.
The development of Internet of Things has been complied in the proposition of edge calculations.Edge calculations are distributed by disposing near access net
Small-sized data center, the open platform being integrated using network, calculating, storage, application power provide IT service for terminal user
With cloud computing ability.
However, being different from traditional centralized cloud data center, edge calculations are considered as a kind of number of network edge formula
According to processing platform, i.e., traditional data center is cut into various small-sized data centers and is placed on access network edge and provide for user
Network service.Therefore, the computing capability that can be provided for edge cloud is limited.How reasonable allocations of edge calculates
In resource have become hot issue.
There are many existing research about resource allocation, but most of documents cannot be applied to scenes of internet of things well, not have
The following can be handled well:
1, in face of huge and isomery internet-of-things terminal user group, how to guarantee the scalability of network, with higher
The service request of resource utilization satisfaction more multi-terminal user；
2, the mobile management of internet-of-things terminal user, such as handover refer in particular to the mobile terminal user of low speed, such as herein
Handheld terminal；
3, the protection of internet-of-things terminal user privacy information；
4, consider the internet-of-things terminal user of high-speed mobile, such as vehicle-mounted internet of things equipment, how to study its mobility.
From the point of view of the development of current Internet of Things, based on the Internet of Things framework of traditional cloud computing, it has been unable to satisfy now such as
Modern internet of things service has complied with Internet of Things for low latency, high reliability and the demand of safety, the rise of mobile edge calculations
The development in net epoch.But compared to traditional cloud computing, edge calculations is applied to scenes of internet of things and are asked there are still urgently to be solved
Topic is badly in need of the efficient and rational resource allocation methods of one kind and meets a large amount of Internet of Things especially for the computing resource finiteness of edge cloud
The mission requirements of network users improve resource utilization.
Summary of the invention
For the problems of existing Internet of Things computational resource allocation, the present invention provides a kind of with efficient system tray
Structure, while considering the power consumption state and computational resource requirements of each terminal user, resource utilization is improved to the maximum extent, is met more
The system and resource allocation methods of the edge calculations of the software definition of the internet of things oriented of multi-user's demand.
In order to achieve the above technical purposes, the technical scheme is that,
A kind of system of the edge calculations of the software definition of internet of things oriented, including multiple multiple accesses in honeycomb deployment
Formula base station equipment, centralized computing resource pool and OpenFlow controller, the base station equipment are used for and multiple and different objects
Networked terminals user communication, base station equipment are equipped with the fringe node for having data-handling capacity and computing capability, the edge
Node is communicatively connected to centralized computing resource pool, and the OpenFlow controller is connected to centralized computing resource pool and is used in combination
In realization centerized fusion.
A kind of system of the edge calculations of the software definition of internet of things oriented, the centralized computing resource pool
Including common resource pool and standby resources pond, the standby resources pond default is in dormant state, when common resource pool total amount
Standby resources pond is then activated when being unable to satisfy calculating demand.
A kind of system of the edge calculations of the software definition of the internet of things oriented, the base station equipment by D2D,
WIFI, bluetooth, narrowband IoT, Zigbee and honeycomb access are communicated with internet-of-things terminal user
A kind of system of the edge calculations of the software definition of internet of things oriented, the fringe node pass through high speed
Optical fiber is communicated to connect with base station equipment and centralized computing resource pool respectively.
A kind of resource allocation methods of the software definition edge calculations of internet of things oriented, based on the system, including with
Lower step:
Step 1: terminal user networks, and proposes calculating task request to OpenFlow controller, and upload mission bit stream；
Step 2:OpenFlow controller is after the task requests for receiving internet-of-things terminal user, first in fringe node
It is upper to distribute special cell, and storage location information and filtering user privacy information for terminal user, it then obtains user and calculates and appoint
The mission bit stream of business；
Step 3:OpenFlow controller using sell computing resource acquisition profit as income, and task based access control information, collection
The capacity of Chinese style computing resource pool, the price of computing resource, the amount of computational resources for user task distribution and user task are held
Bring unit cost establishes the edge cloud i.e. utility function of centralized computing resource pool one end when row, while internet-of-things terminal is used
Family uploads to edge cloud using task and executes saved time delay as income, and whether task based access control is held in centralized computing resource pool
Row, mission bit stream, the computing capability of internet-of-things terminal user local, the price of computing resource, controller are internet-of-things terminal use
Rate that the amount of computational resources and task data of family distribution upload establishes the utility function of internet-of-things terminal user one end；
Step 4: according to step 3, OpenFlow controller preferentially provides initial price, which determines user demand
The payable expense of per unit computing resource institute；
Step 5: the utility function that each internet-of-things terminal user establishes according to step 3, and on the basis for meeting constraint condition
On, the optimal benefit of optimal amount of computational resources and terminal user needed for acquiring；
Step 6: controller receives the feedback from each terminal user, according to the resulting computational resource requirements total amount of step 5,
Update the use for fixing a price and determining centralized computing resource pool；The computing resource total amount required for internet-of-things terminal user is more than
More than the total amount of common resource pool, and resource pricing is lower than unit cost, then controller increases resource pricing；Otherwise ratio is reduced
Resource pricing；
Step 7: the resource pricing updated according to step 6, in the range of postponing allows, internet-of-things terminal user counts again
Calculate number of resources needed for adjusting and optimum utility；
Step 8: by successive ignition until both sides' no longer adjustable strategies, i.e. controller does not rechange price and enables resource
The decision in pond, internet-of-things terminal user no longer adjust required number of resources, or strategy gained benefit is minimum no more than presetting twice
Value, then obtain optimal resource allocation strategy.
A kind of resource allocation methods of the software definition edge calculations of internet of things oriented are appointed in the step 1
Information of being engaged in includes task data amount size d, calculation amount size s, largest tolerable time delay tmax, transmission power piAnd surplus equipment
ENERGY Ere。
A kind of resource allocation methods of the software definition edge calculations of internet of things oriented, institute in the step 2
The special cell stated, after internet-of-things terminal user leaves network or completes calculating task, special cell will be released.
A kind of resource allocation methods of the software definition edge calculations of internet of things oriented, the internet-of-things terminal
The utility function of user i indicates are as follows:
Wherein, when internet-of-things terminal user uploads to the i.e. centralized computing resource pool of edge cloud with task and executes saved
Prolong as income, uses UiIt indicates；xiWhether the task of internet-of-things terminal user executes in edge cloud, and value is 0 or 1, when value is
Task of internet-of-things terminal user is then characterized when 1 is executed in edge cloud；λiIndicate that internet-of-things terminal user i saves time delay
Preference；fi lIndicate the local computing capability of internet-of-things terminal user；fiIndicate that controller is the calculating of user distribution
Stock number；A indicates the resource pricing that controller provides；rI, oIt indicates the rate that data upload, is had using shannon formula:
Wherein, B characterizes channel width；σ2For the noise power of white Gaussian noise；hI, oFor channel gain；piIt is set for Internet of Things
Standby transmission power；
Above-mentioned utility function also needs to meet the basic constraint condition of following two:
First constraint condition characterizes the execution time of entire taskIt must not exceed the tolerable maximum of user task
Time delayEnergy consumption caused by second constraint condition characterization is uploaded as taskIt must not exceed the surplus of terminal device
Complementary energy
Controller, that is, edge cloud utility function indicates are as follows:
Wherein, controller uses U using the profit for selling computing resource acquisition as incomeECIt indicates；C indicates centralized resources pond
Total capacity, α characterize user task execute when bring unit cost；feIndicate the stock number in the standby resources pond enabled；Y table
Show the unit cost as caused by activation standby resources pond.
The technical effects of the invention are that first proposed a kind of novel system architecture.In view of existing Internet of Things industry
The requirement of the low delay, high reliability of business, and the inadaptability of traditional Internet of Things framework based on cloud computing, are moved for low speed
The mobility and privacy concern at family are employed, software defined network SDN (Software Defined Networking) and net are introduced
The thought of network virtualization of function NFV (Network Function Virtualization), system structure is divided from level
For terminal device layer, data Layer is centralized computing resource pool and network control layer.Mask data level and control plane,
Network function is decoupled from hardware device, centerized fusion is formed, upwardly through programmable application programming interfaces API
(Application Programming Interface) execution mobile management, data processing, resource allocation function, downwards
It is communicated by OpenFlow interface with transponder, realizes the forwarding of user data.Meanwhile standby resources pond is configured, default is in
Dormant state, to save equipment operation bring energy expense, when facing a large amount of terminal user's task requests that happen suddenly, through controlling
Whether device execution activates behavior, provides service.
Secondly on the basis of provided system architecture, for the distribution of edge calculations resource, construct it is single it is main mostly from
Si Tankeer Burger game, wherein based on controller, internet-of-things terminal user is from the basis for ensureing QoS of customer
On, for each opposite sex of terminal device, by Si Tankeer Burger game applications to the distribution of internet-of-things terminal user's computing resource
In the process, the power consumption state and computational resource requirements for considering each terminal user improve resource utilization to the maximum extent, meet more
The demand of multi-user.
Detailed description of the invention
Fig. 1 is system structure diagram of the invention；
Fig. 2 is multiple access base station schematic diagram of the invention；
Fig. 3 is controller and interface diagram of the invention；
Fig. 4 is flow chart of the method for the present invention.
Specific embodiment
Research and development of the invention are by project of national nature science fund project 61672539, and 61672537,61803394,
61873353,61772558, which provide part, supports.The advantages of being virtualized in view of software defined network and network function and object
The characteristics of networking service, the present invention provides a kind of novel network architectures, and proposition is smooth based on this on the basis of this framework
The resource allocation methods of Ke Er Burger game.The present invention is further described in detail now in conjunction with attached drawing.
Referring to Fig. 1, present invention introduces software defined networks and network function virtualization to calculate, logically by whole network
It is divided into following three layers: client layer, edge cloud layer and control layer.Client layer is the wireless base station being distributed in honeycomb, simultaneously
Each base station nearby connects a fringe node EN (Edge Node) by high speed fibre, and EN is one and has calculating, storage
With the server of data analysis function, it is responsible for terminal device and special cell is provided or makees private resource block, for storing position
Confidence breath, filters the personal information of terminal user.Edge cloud layer is the computing resource pool that entity is high-performance server cluster, is born
Duty executes the calculating task of terminal user.The present invention enables a standby resources pond, and default is in a dormant state to save clothes
Be engaged in device energy, when in face of a large amount of calculating tasks request when and preceding total resources be unable to satisfy when, can quickly activate standby resources pond.
Edge cloud layer passes through high speed fibre and exchanges such as user plane communication.Control layer be an OpenFlow controller, realize centerized fusion with
Network function management.
Referring to fig. 2, it is contemplated that under scenes of internet of things, the diversity and terminal equipment access network mode of terminal device
Each opposite sex, for example smart phone, by WIFI connection, digital camera is networked by bluetooth connection, between intelligent terminal with
D2D mode communicates.Therefore, base station has a variety of access technologies in the present invention, including D2D, WIFI, bluetooth, narrowband IoT,
Zigbee and honeycomb access.
Referring to Fig. 3, the basic function of OpenFlow controller is to establish, maintenance stream by calculating data forwarding paths
Table information, and the forward process according to flow table information control data.Controller passes downwardly through OpenFlow agreement and forwarding device
Communication, connect with network function module upwardly through programmable application programming interfaces, realizes specific functional application and resource
Distribution, mobile management.
When executing the method for the present invention, the participant of edge calculations resource allocation process clear first, i.e. terminal SU
(Smart User) and OpenFlow controller.It is clear single main mostly from the leader in Si Tankeer Burger game, i.e.,
OpenFlow controller and follower, i.e. internet-of-things terminal user SU.It is timely to specify internet-of-things terminal user's calculating task demand
Prolong and power consumption constraint, resource tankage and cost coefficient.The utility function and constraint condition for specifying both sides, according to internet of things equipment
Power consumption state and bandwidth demand, design different utility functions for different types of internet-of-things terminal user.
Fig. 4 show flow chart of the method for the present invention.Specific implementation step is as follows:
Step 1: terminal user networks, and proposes calculating task request, and upper mission bit stream to OpenFlow controller, specifically
Content includes task data amount size d, calculation amount size s, largest tolerable time delay tmax, transmission power piAnd surplus equipment energy
Measure Ere。
Step 2: controller is first eventually by fringe node EN after the task requests for receiving internet-of-things terminal user
End subscriber distributes special cell, management position information, and filtering user privacy information, secondly obtains the request of user's calculating task
Relevant information.
Step 3: gambling process, as leader, preferentially provides decision, terminal device is as follower's foundation by controller
The decision of controller adjusts the strategy of oneself, guarantees optimal benefit.Wherein, the utility function of internet-of-things terminal user i can be with table
It is shown as:
Wherein, internet-of-things terminal user uploads to edge cloud using task and executes saved time delay as income, uses UiIt indicates；
xiWhether the task of internet-of-things terminal user executes in edge cloud, and value is 0 or 1, and Internet of Things end is then characterized when value is 1
The task of end subscriber is executed in edge cloud；λiIndicate the preference that internet-of-things terminal user i saves time delay；fi lIt indicates
The local computing capability of internet-of-things terminal user；fiIndicate that controller is the amount of computational resources of user distribution；A indicates controller
The resource pricing provided；rI, oIt indicates the rate that data upload, can be obtained using shannon formula:
Wherein, B characterizes channel width；σ2For the noise power of white Gaussian noise；hI, oFor channel gain；piIt is set for Internet of Things
Standby transmission power, it is contemplated that the transmission power of each opposite sex of internet of things equipment, different Internet of Things network users is different.
In view of equipment dump energy difference and the diversity of user task caused by each opposite sex of internet-of-things terminal equipment
The difference of caused delay requirement, above-mentioned utility function also need to meet the basic constraint condition of following two:
When the execution time that first constraint condition characterizes entire task must not exceed the tolerable maximum of user task
Prolong, energy consumption caused by second constraint condition characterization is uploaded as task must not exceed the dump energy of terminal device.
Controller, that is, edge cloud utility function can indicate are as follows:
Wherein, controller uses U using the profit for selling computing resource acquisition as incomeECIt indicates；C indicates centralized resources pond
Total capacity, α characterize user task execute when bring unit cost；feIndicate the stock number in the standby resources pond enabled；Y table
Show the unit cost as caused by activation standby resources pond.
Step 4: according to step 3, OpenFlow controller preferentially provides initial price, which determines user demand
The per unit computing resource payable expense a of institute.
Step 5: the utility function that each internet-of-things terminal user arranges according to step 3, and on the basis for meeting constraint condition
On, the optimal benefit of optimal amount of computational resources and terminal user needed for acquiring.
Step 6: controller receives the feedback from each terminal user, according to the resulting computational resource requirements total amount of step 5,
It updates price or decides whether to enable standby resources pond.The computing resource total amount required for internet-of-things terminal user is more than
The total amount of common resource pool, and resource pricing is lower than unit cost, then controller increases resource pricing；Otherwise ratio reduces resource
Price.
Step 7: the resource pricing updated according to step 6, in the range of postponing allows, internet-of-things terminal user counts again
Calculate number of resources needed for adjusting and optimum utility；
Step 8: by successive ignition until both sides' no longer adjustable strategies, i.e. controller does not rechange price and enables resource
The decision in pond, internet-of-things terminal user no longer adjust required number of resources, or twice strategy gained benefit be no more than it is one minimum
Value, then obtain optimal resource allocation strategy.
Claims (8)
1. a kind of system of the edge calculations of the software definition of internet of things oriented, which is characterized in that including multiple in honeycomb portion
The multiple access formula base station equipment of administration, centralized computing resource pool and OpenFlow controller, the base station equipment be used for it is more
A different internet-of-things terminal user communication, base station equipment are equipped with the fringe node for having data-handling capacity and computing capability,
The fringe node is communicatively connected to centralized computing resource pool, and the OpenFlow controller is connected to centralized calculating
Resource pool and for realizing centerized fusion.
2. a kind of system of the edge calculations of the software definition of internet of things oriented according to claim 1, which is characterized in that
The centralized computing resource pool includes common resource pool and standby resources pond, and the standby resources pond default is in suspend mode
State then activates standby resources pond when common resource pool total amount is unable to satisfy calculating demand.
3. a kind of system of the edge calculations of the software definition of internet of things oriented according to claim 1, which is characterized in that
The base station equipment is accessed by D2D, WIFI, bluetooth, narrowband IoT, Zigbee and honeycomb come logical with internet-of-things terminal user
Letter.
4. a kind of system of the edge calculations of the software definition of internet of things oriented according to claim 1, which is characterized in that
The fringe node is communicated to connect with base station equipment and centralized computing resource pool respectively by high speed fibre.
5. a kind of resource allocation methods of the software definition edge calculations of internet of things oriented, which is characterized in that be based on claim
Any system of 1-4, comprising the following steps:
Step 1: terminal user networks, and proposes calculating task request to OpenFlow controller, and upload mission bit stream；
Step 2:OpenFlow controller is on fringe node first after the task requests for receiving internet-of-things terminal user
Terminal user distributes special cell, and storage location information and filtering user privacy information, then obtains user's calculating task
Mission bit stream；
Step 3:OpenFlow controller is to sell the profit of computing resource acquisition as income, and task based access control information, centralization
When the capacity of computing resource pool, the price of computing resource, the amount of computational resources for user task distribution and user task execute
Bring unit cost establishes the utility function of the i.e. centralized computing resource pool one end of edge cloud, at the same internet-of-things terminal user with
It is income that task, which uploads to edge cloud and executes saved time delay, and task based access control whether execute in centralized computing resource pool,
Mission bit stream, the computing capability of internet-of-things terminal user local, the price of computing resource, controller are internet-of-things terminal user point
The rate that the amount of computational resources and task data matched upload establishes the utility function of internet-of-things terminal user one end；
Step 4: according to step 3, OpenFlow controller preferentially provides initial price, which determines every list of user demand
The payable expense of position computing resource institute；
Step 5: the utility function that each internet-of-things terminal user establishes according to step 3, and on the basis of meeting constraint condition, it asks
The optimal benefit of optimal amount of computational resources and terminal user needed for obtaining；
Step 6: controller receives the feedback from each terminal user, according to the resulting computational resource requirements total amount of step 5, updates
Fix a price and determine the use of centralized computing resource pool；The computing resource total amount required for internet-of-things terminal user is more than
The total amount of common resource pool, and resource pricing is lower than unit cost, then controller increases resource pricing；Otherwise ratio reduces resource
Price；
Step 7: the resource pricing updated according to step 6, in the range of postponing allows, internet-of-things terminal user calculates tune again
Number of resources needed for whole and optimum utility；
Step 8: by successive ignition until both sides' no longer adjustable strategies, i.e. controller does not rechange price and enables resource pool
Decision, internet-of-things terminal user no longer adjust required number of resources, or strategy gained benefit is no more than default minimum twice, then
Obtain optimal resource allocation strategy.
6. a kind of resource allocation methods of the software definition edge calculations of internet of things oriented according to claim 5, special
Sign is that mission bit stream includes task data amount size d, calculation amount size s, largest tolerable time delay in the step 1
tmax, transmission power piAnd surplus equipment ENERGY Ere。
7. a kind of resource allocation methods of the software definition edge calculations of internet of things oriented according to claim 5, special
Sign is, special cell described in the step 2, after internet-of-things terminal user leaves network or completes calculating task,
Special cell will be released.
8. a kind of resource allocation methods of the software definition edge calculations of internet of things oriented according to claim 6, special
Sign is that the utility function of the internet-of-things terminal user i indicates are as follows:
Wherein, internet-of-things terminal user, which with task uploads to the i.e. centralized computing resource pool of edge cloud and executes saved time delay, is
Income uses UiIt indicates；xiWhether the task of internet-of-things terminal user executes in edge cloud, and value is 0 or 1, when value is 1
Then the characterizing internet-of-things terminal user of the task is executed in edge cloud；λiIndicate what internet-of-things terminal user i saved time delay
Preference；fi lIndicate the local computing capability of internet-of-things terminal user；fiIndicate the calculating money that controller is user distribution
Source amount；A indicates the resource pricing that controller provides；ri,oIt indicates the rate that data upload, is had using shannon formula:
Wherein, B characterizes channel width；σ2For the noise power of white Gaussian noise；hi,oFor channel gain；piFor internet of things equipment
Transmission power；
Above-mentioned utility function also needs to meet the basic constraint condition of following two:
First constraint condition characterizes the execution time of entire taskIt must not exceed the tolerable maximum delay of user taskEnergy consumption caused by second constraint condition characterization is uploaded as taskIt must not exceed the residual energy of terminal device
Amount
Controller, that is, edge cloud utility function indicates are as follows:
Wherein, controller uses U using the profit for selling computing resource acquisition as incomeECIt indicates；C indicates the total of centralized resources pond
Capacity, α characterize bring unit cost when user task executes；feIndicate the stock number in the standby resources pond enabled；Y indicate by
In activating unit cost caused by standby resources pond.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910172114.7A CN109981753B (en) | 2019-03-07 | 2019-03-07 | Software-defined edge computing system and resource allocation method for Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910172114.7A CN109981753B (en) | 2019-03-07 | 2019-03-07 | Software-defined edge computing system and resource allocation method for Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109981753A true CN109981753A (en) | 2019-07-05 |
| CN109981753B CN109981753B (en) | 2021-04-27 |
Family
ID=67078148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910172114.7A Active CN109981753B (en) | 2019-03-07 | 2019-03-07 | Software-defined edge computing system and resource allocation method for Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109981753B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110519374A (en) * | 2019-08-28 | 2019-11-29 | 西南大学 | The edge calculations method and its fringe node of ZigBee-network chemical industry control system |
| CN110557732A (en) * | 2019-08-05 | 2019-12-10 | 西北工业大学 | vehicle edge computing network task unloading load balancing system and balancing method |
| CN110650487A (en) * | 2019-09-27 | 2020-01-03 | 常熟理工学院 | Internet of things edge computing configuration method based on data privacy protection |
| CN111679905A (en) * | 2020-05-11 | 2020-09-18 | 天津大学 | Calculation network fusion network model |
| CN112311834A (en) * | 2019-08-02 | 2021-02-02 | 阿里巴巴集团控股有限公司 | Method and system for describing and distributing multi-stage computing of edge cloud |
| CN112596910A (en) * | 2020-12-28 | 2021-04-02 | 广东电网有限责任公司电力调度控制中心 | Cloud computing resource scheduling method in multi-user MEC system |
| CN112995280A (en) * | 2021-02-03 | 2021-06-18 | 北京邮电大学 | Data distribution method and device for multi-content demand service |
| CN113098891A (en) * | 2021-04-19 | 2021-07-09 | 广东技术师范大学 | Method and system for network transmission control based on medical big data |
| CN113315806A (en) * | 2021-04-14 | 2021-08-27 | 深圳大学 | Multi-access edge computing architecture for cloud network fusion |
| CN113760514A (en) * | 2021-11-10 | 2021-12-07 | 北京航空航天大学杭州创新研究院 | Internet of things task scheduling method and device and readable storage medium |
| CN114513838A (en) * | 2022-02-28 | 2022-05-17 | 中国农业银行股份有限公司 | Moving edge calculation method, frame, and medium |
| CN116208564A (en) * | 2023-02-22 | 2023-06-02 | 北京乐研科技股份有限公司 | High-performance Internet of things scheduling method and system based on X86 platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104486218A (en) * | 2014-12-16 | 2015-04-01 | 上海斐讯数据通信技术有限公司 | MPLS network control system and method based on SDN |
| CN105407056A (en) * | 2014-09-16 | 2016-03-16 | 中国电信股份有限公司 | Method and system for establishing service chain in software-defined network |
| US20160112246A1 (en) * | 2014-10-17 | 2016-04-21 | International Business Machines Corporation | Identifying configuration inconsistency in edge-based software defined networks (sdn) |
| CN109286508A (en) * | 2017-07-19 | 2019-01-29 | 中兴通讯股份有限公司 | A kind of mist node deployment method and system |
-
2019
- 2019-03-07 CN CN201910172114.7A patent/CN109981753B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105407056A (en) * | 2014-09-16 | 2016-03-16 | 中国电信股份有限公司 | Method and system for establishing service chain in software-defined network |
| US20160112246A1 (en) * | 2014-10-17 | 2016-04-21 | International Business Machines Corporation | Identifying configuration inconsistency in edge-based software defined networks (sdn) |
| CN104486218A (en) * | 2014-12-16 | 2015-04-01 | 上海斐讯数据通信技术有限公司 | MPLS network control system and method based on SDN |
| CN109286508A (en) * | 2017-07-19 | 2019-01-29 | 中兴通讯股份有限公司 | A kind of mist node deployment method and system |
Non-Patent Citations (1)
| Title |
|---|
| 史晨华: "基于边缘计算的5G低时延高可靠业务卸载策略研究", 《中国优秀硕士学位论文全文数据库信息科技辑（月刊）2019年第02期》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112311834A (en) * | 2019-08-02 | 2021-02-02 | 阿里巴巴集团控股有限公司 | Method and system for describing and distributing multi-stage computing of edge cloud |
| CN112311834B (en) * | 2019-08-02 | 2022-08-30 | 阿里巴巴集团控股有限公司 | Method and system for describing and distributing multi-stage computing of edge cloud |
| CN110557732A (en) * | 2019-08-05 | 2019-12-10 | 西北工业大学 | vehicle edge computing network task unloading load balancing system and balancing method |
| CN110519374B (en) * | 2019-08-28 | 2021-09-28 | 西南大学 | Edge computing method of ZigBee networked industrial control system and edge node thereof |
| CN110519374A (en) * | 2019-08-28 | 2019-11-29 | 西南大学 | The edge calculations method and its fringe node of ZigBee-network chemical industry control system |
| CN110650487A (en) * | 2019-09-27 | 2020-01-03 | 常熟理工学院 | Internet of things edge computing configuration method based on data privacy protection |
| CN110650487B (en) * | 2019-09-27 | 2022-10-28 | 常熟理工学院 | Internet of things edge computing configuration method based on data privacy protection |
| CN111679905A (en) * | 2020-05-11 | 2020-09-18 | 天津大学 | Calculation network fusion network model |
| CN111679905B (en) * | 2020-05-11 | 2022-03-08 | 天津大学 | Calculation network fusion network model system |
| CN112596910A (en) * | 2020-12-28 | 2021-04-02 | 广东电网有限责任公司电力调度控制中心 | Cloud computing resource scheduling method in multi-user MEC system |
| CN112596910B (en) * | 2020-12-28 | 2024-02-20 | 广东电网有限责任公司电力调度控制中心 | Cloud computing resource scheduling method in multi-user MEC system |
| CN112995280B (en) * | 2021-02-03 | 2022-04-22 | 北京邮电大学 | Data distribution method and device for multi-content demand service |
| CN112995280A (en) * | 2021-02-03 | 2021-06-18 | 北京邮电大学 | Data distribution method and device for multi-content demand service |
| CN113315806A (en) * | 2021-04-14 | 2021-08-27 | 深圳大学 | Multi-access edge computing architecture for cloud network fusion |
| CN113098891A (en) * | 2021-04-19 | 2021-07-09 | 广东技术师范大学 | Method and system for network transmission control based on medical big data |
| CN113760514A (en) * | 2021-11-10 | 2021-12-07 | 北京航空航天大学杭州创新研究院 | Internet of things task scheduling method and device and readable storage medium |
| CN113760514B (en) * | 2021-11-10 | 2022-03-22 | 北京航空航天大学杭州创新研究院 | Internet of things task scheduling method and device and readable storage medium |
| CN114513838A (en) * | 2022-02-28 | 2022-05-17 | 中国农业银行股份有限公司 | Moving edge calculation method, frame, and medium |
| CN116208564A (en) * | 2023-02-22 | 2023-06-02 | 北京乐研科技股份有限公司 | High-performance Internet of things scheduling method and system based on X86 platform |
| CN116208564B (en) * | 2023-02-22 | 2023-12-15 | 北京乐研科技股份有限公司 | High-performance Internet of things scheduling method and system based on X86 platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109981753B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109981753A (en) | A kind of system and resource allocation methods of the edge calculations of the software definition of internet of things oriented | |
| Yi et al. | A multi-user mobile computation offloading and transmission scheduling mechanism for delay-sensitive applications | |
| US11601512B2 (en) | System and method for throttling service requests having non-uniform workloads | |
| Yang et al. | Catalyzing cloud-fog interoperation in 5G wireless networks: An SDN approach | |
| Bittencourt et al. | Mobility-aware application scheduling in fog computing | |
| CN110187973A (en) | A kind of service arrangement optimization method towards edge calculations | |
| WO2016161677A1 (en) | Traffic offload method and system | |
| US8953453B1 (en) | System and method for throttling service requests using work-based tokens | |
| CN109041130B (en) | Resource allocation method based on mobile edge calculation | |
| CN107995660A (en) | Support Joint Task scheduling and the resource allocation methods of D2D- Edge Servers unloading | |
| CN103747274B (en) | A kind of video data center setting up cache cluster and cache resources dispatching method thereof | |
| CN104092756A (en) | Cloud storage system resource dynamic allocation method based on DHT mechanism | |
| Yi et al. | A queueing game based management framework for fog computing with strategic computing speed control | |
| CN110177055B (en) | Pre-allocation method of edge domain resources in edge computing scene | |
| Rui et al. | Computation offloading in a mobile edge communication network: A joint transmission delay and energy consumption dynamic awareness mechanism | |
| CN108881509A (en) | A kind of DNS query method and device based on HTTPDNS | |
| Sun et al. | Energy-efficient multimedia task assignment and computing offloading for mobile edge computing networks | |
| CN112600761B (en) | Resource allocation method, device and storage medium | |
| CN113419867B (en) | Energy-saving service supply method in edge-oriented cloud collaborative computing environment | |
| WO2023116460A1 (en) | Multi-user multi-task computing offloading method and system in mobile edge computing environment | |
| Chen et al. | Latency minimization for mobile edge computing networks | |
| CN104714845B (en) | Resource dynamic regulation method, device and more kernel operating systems | |
| Akki et al. | Energy efficient resource scheduling using optimization based neural network in mobile cloud computing | |
| CN114691372A (en) | Group intelligent control method of multimedia end edge cloud system | |
| CN109995890A (en) | A kind of method and server managing network address translation NAT gateway |
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 |