CN108900315B - Service profit optimization method for cloud service provider - Google Patents

Service profit optimization method for cloud service provider Download PDF

Info

Publication number
CN108900315B
CN108900315B CN201810897176.XA CN201810897176A CN108900315B CN 108900315 B CN108900315 B CN 108900315B CN 201810897176 A CN201810897176 A CN 201810897176A CN 108900315 B CN108900315 B CN 108900315B
Authority
CN
China
Prior art keywords
service provider
cloud service
profit
bandwidth
algorithm
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
Application number
CN201810897176.XA
Other languages
Chinese (zh)
Other versions
CN108900315A (en
Inventor
崔勇
杨振杰
刘亚东
张知行
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Original Assignee
Tsinghua University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tsinghua University filed Critical Tsinghua University
Priority to CN201810897176.XA priority Critical patent/CN108900315B/en
Publication of CN108900315A publication Critical patent/CN108900315A/en
Application granted granted Critical
Publication of CN108900315B publication Critical patent/CN108900315B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/02—Details
    • H04L12/14—Charging, metering or billing arrangements for data wireline or wireless communications
    • H04L12/1442—Charging, metering or billing arrangements for data wireline or wireless communications at network operator level
    • H04L12/145—Charging, metering or billing arrangements for data wireline or wireless communications at network operator level trading network capacity or selecting route based on tariff
    • 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
    • H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H04L43/0882—Utilisation of link capacity
    • 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
    • H04L41/142—Network analysis or design using statistical or mathematical methods

Abstract

The cloud service provider-oriented service profit optimization method is a scheme for solving the problem of maximization of profit of a cloud service provider by combining the existing algorithm for solving the problem of maximization of service income of the cloud service provider and the problem of minimization of service expense of the cloud service provider. The scheme execution flow comprises the following steps: 1) inputting a transmission request, a network topology and a link bandwidth unit price in a network, which are received by a cloud service provider; 2) and combining the existing minimum service expense algorithm and the maximum service income algorithm, and iteratively calculating the maximum service profit by using the two algorithms according to the algorithm framework flow. The invention can directly improve the operation profit of the cloud service provider by utilizing the prior related technology.

Description

Service profit optimization method for cloud service provider
Technical Field
The invention belongs to the technical field of internet, relates to a traffic scheduling technology and a service request selection technology, and particularly relates to a service profit optimization method for a cloud service provider.
Background
Many cloud service providers maintain multiple data centers to support their businesses, such as microsoft, google. The data centers run various globally distributed applications and are distributed in different geographic areas, which determines that the data centers have the requirement of mutual communication across the geographic areas, and the data center wide area network provides network connection for the data center nodes distributed across the geographic areas. The cloud service provider may receive the transmission request of the application, and a portion of the fee may be charged from the cloud user when the cloud service provider receives the transmission request, the portion being revenue of the cloud service provider. Meanwhile, the cloud service provider transmits data on the data center wide area network, and the network provider is also paid a certain fee, which is used as the expense of the cloud service provider. With increasingly intense business competition, maximizing service profit is crucial for cloud service providers. Even though algorithms exist that maximize service revenue or minimize service expenditure. But planning the requests to maximize the profit of the cloud service provider is difficult because the routing paths of different requests are strongly coupled together in the network.
Much research work has emerged in recent years around the deployment of rational scheduling of large flows. One of the main ideas is to add a storage device to a data center, and to select whether to store or forward data when the data arrives, i.e. a store-and-forward strategy. The first work proposes that the arriving data is temporarily stored when the link is busy, the data is transmitted when the link is idle, and finally the utilization rate of the bandwidth is improved in the time dimension so as to reduce the network cost of the cloud service provider. Another work is to charge the user by modifying the existing charging model and adopting a dynamic price mode, but there are certain problems and risks in modifying the cloud service provider charging model.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a cloud service provider-oriented service profit optimization method, which utilizes the existing service profit maximization algorithm and service support minimization algorithm to solve the problem of service profit maximization for the cloud service provider.
In order to achieve the purpose, the invention adopts the technical scheme that:
the service profit optimization method for the cloud service provider is mainly characterized in that the service profit optimization method is realized in a network of the cloud service provider according to the following steps:
step (1), dividing a lease period into a plurality of transmission time slots, namely 1, …, T, representing links between the data centers by a directed graph G ═ V, E, wherein V is a set of nodes of the directed graph and represents a set of all the data centers, E is a set of links of the directed graph and represents a set of all the links, and six-element group r is used for representing the link between the data centers and the data centersi＝(si,ti,di,ai,τi,vi) To represent a large stream, where si，ti，di，ai，τi,viRespectively represent the ith requestThe source node, the destination node, the transmission rate, the arrival time, the deadline and the value obtained by the cloud service provider for meeting the transmission requirement;
step (2), for the received request, the minimum transmission bandwidth cost algorithm under the fixed condition of the existing transmission request solving is utilized to solve the minimum bandwidth cost required when all the requests are received, and the bandwidth value c corresponding to the link e is obtained according to the algorithmeAnd receiving a profit P for all requested conditions;
step (3) of subjecting c obtained in step (2) toeConsider the bandwidth capacity upper bound of link e in the network. For the link with the link utilization rate less than the threshold value tau, the upper bound of the bandwidth is changed into tau times (0) of the original upper bound<τ<1)；
And (4) calculating the received request set and the corresponding used network bandwidth by utilizing the existing algorithm for solving the total profit maximization in the network under the bandwidth fixed condition according to the bandwidth capacity upper bound obtained in the step (3). If the solved network profit is larger than the existing solution P, updating the solution P;
and (5) judging whether the iteration times are greater than a threshold value J, if so, finishing the algorithm to generate a scheduling scheme, otherwise, skipping to the step (2)
Compared with the prior art, the invention has the beneficial effects that:
1) the invention simultaneously considers the income and expenditure of the cloud service provider and further improves the profit of the cloud service provider.
2) The scheme provided by the invention considers that the ISP charges according to a certain granularity, and the practicability is stronger.
3) The scheme provided by the invention does not need to introduce additional storage equipment or modify the existing charging mode, thereby greatly reducing the difficulty in use and deployment.
Drawings
Fig. 1 is a detailed flowchart of a service profit maximization method for a cloud service provider.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the drawings and examples.
The service profit optimization method for the cloud service provider is realized in the network of the cloud service provider according to the following steps:
step (1), dividing a lease period into a plurality of transmission time slots, namely 1, …, T, representing links between the data centers by a directed graph G ═ V, E, wherein V is a set of nodes of the directed graph and represents a set of all the data centers, E is a set of links of the directed graph and represents a set of all the links, and six-element group r is used for representing the link between the data centers and the data centersi＝(si,ti,di,ai,τi,vi) To represent a large stream, where si，ti，di，ai，τi,viRespectively representing the source node, the destination node, the transmission rate, the arrival time, the deadline of the ith request and the value obtained by the cloud service provider for meeting the transmission requirement;
step (2), for the received request, the minimum transmission bandwidth cost algorithm under the fixed condition of the existing transmission request solving is utilized to solve the minimum bandwidth cost required when all the requests are received, and the bandwidth value c corresponding to the link e is obtained according to the algorithmeAnd receiving a profit P for all requested conditions;
by LiRepresenting from the origin siTo the target node tiWhen K flow requests are received, the revenue of the cloud service provider may be expressed as:
Figure GDA0002401497450000031
and is
Figure GDA0002401497450000032
Wherein xi,jIndicating whether request i passes through jth path.
Figure GDA0002401497450000033
Indicating that the cloud service provider satisfies the request, and charging a value viThe cost of (2).
Figure GDA0002401497450000034
Indicating that the cloud service provider rejects the request
When the cloud service provider transmits a traffic request for a user, the cost provided to the network service provider (ISP), i.e., the expense of the cloud service provider, can be expressed as:
Figure GDA0002401497450000035
wherein, ceBandwidth value, u, charged for ISP on edge eeRepresenting the unit price of each edge e, ceThe specific calculation method of (1) is as follows:
Figure GDA0002401497450000041
wherein r isi,tIndicating the transmission rate of the i request at time t
Figure GDA0002401497450000042
Ii,j,eAnd indicating whether the jth path of the ith flow request passes through the e link, if so, the jth path is 1, and otherwise, the jth path is 0.
The revenue for the network service provider can be expressed as: p ═ I-C
Step (3) of subjecting c obtained in step (2) toeConsider the bandwidth capacity upper bound of link e in the network. According to the formula
Figure GDA0002401497450000043
The utilization of link e is calculated. T is the number of slots of the charging period. For the link with the link utilization rate less than the threshold value tau, the upper bound of the bandwidth is changed into tau times (0) of the original upper bound<τ<1) I.e. ce＝τce；
Step (4), according to the bandwidth capacity upper bound c obtained in step (3)eCalculating the received request set by using the existing algorithm for solving the total profit maximization in the network under the condition of fixed bandwidth, namely solving the result xi,jIn satisfy
Figure GDA0002401497450000044
The set of requests i, and the network bandwidth used accordingly. If the solved network profit is larger than the existing solution P, updating the solution P;
and (5) judging whether the iteration times are greater than a threshold value J or not by once iteration from the step (2) to the step (4), if so, finishing the algorithm to generate a scheduling scheme, and otherwise, skipping to the step (2).
In conclusion, the invention provides a service profit optimization scheme for cloud service providers. The scheme can simultaneously optimize service income and service expenditure, does not introduce additional storage expenditure, and does not need to modify the existing charging mode. Under the premise, the scheme greatly improves the profit of the cloud service provider.

Claims (1)

1. The service profit optimization method for the cloud service provider is mainly characterized in that the service profit optimization method is realized in a network of the cloud service provider according to the following steps:
step (1), dividing a lease period into a plurality of transmission time slots, namely 1, …, T, representing links between the data centers by a directed graph G ═ V, E, wherein V is a set of nodes of the directed graph and represents a set of all the data centers, E is a set of links of the directed graph and represents a set of all the links, and six-element group r is used for representing the link between the data centers and the data centersi＝(si,ti,di,ai,τi,vi) To represent a large stream, where si，ti，di，ai，τi,viRespectively representing the source node, the destination node, the transmission rate, the arrival time, the deadline of the ith request and the value obtained by the cloud service provider for meeting the transmission requirement;
step (2), for the received request, the minimum transmission bandwidth cost algorithm under the fixed condition of the existing transmission request solving is utilized to solve the minimum bandwidth cost required when all the requests are received, and the bandwidth value c corresponding to the link e is obtained according to the algorithmeAnd receiving a profit P for all requested conditions;
step (3) of subjecting c obtained in step (2) toeRegarding the link e in the network as the upper bound of the bandwidth capacity, for the link with the link utilization rate less than the threshold tau, the upper bound of the bandwidth capacity is changed into tau times of the original upper bound, 0<τ<1；
Step (4), according to the upper bound of the bandwidth capacity obtained in the step (3), calculating a received request set and a correspondingly used network bandwidth by utilizing the existing algorithm for solving the total profit maximization in the network under the bandwidth fixed condition, and if the solved network profit is larger than the existing solution P, updating the solution P;
and (5) judging whether the iteration times are greater than a threshold value J, if so, finishing the algorithm to generate a scheduling scheme, and otherwise, jumping to the step (2).
CN201810897176.XA 2018-08-08 2018-08-08 Service profit optimization method for cloud service provider Active CN108900315B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810897176.XA CN108900315B (en) 2018-08-08 2018-08-08 Service profit optimization method for cloud service provider

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810897176.XA CN108900315B (en) 2018-08-08 2018-08-08 Service profit optimization method for cloud service provider

Publications (2)

Publication Number Publication Date
CN108900315A CN108900315A (en) 2018-11-27
CN108900315B true CN108900315B (en) 2020-06-09

Family

ID=64353252

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810897176.XA Active CN108900315B (en) 2018-08-08 2018-08-08 Service profit optimization method for cloud service provider

Country Status (1)

Country Link
CN (1) CN108900315B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106060145A (en) * 2016-06-22 2016-10-26 北京交通大学 Profit based request access control method in distributed multi-cloud data center
CN107454009A (en) * 2017-09-08 2017-12-08 清华大学 The offline scenario low bandwidth overhead flow scheduling scheme at data-oriented center

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10452451B2 (en) * 2016-06-10 2019-10-22 Board Of Regents, The University Of Texas System Systems and methods for scheduling of workload-aware jobs on multi-clouds

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106060145A (en) * 2016-06-22 2016-10-26 北京交通大学 Profit based request access control method in distributed multi-cloud data center
CN107454009A (en) * 2017-09-08 2017-12-08 清华大学 The offline scenario low bandwidth overhead flow scheduling scheme at data-oriented center

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Geo-Distributed BigData Processing for Maximizing Profit in Federated Clouds Environment;Thouraya Gouasmi等;《2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP)》;20180607;全文 *

Also Published As

Publication number Publication date
CN108900315A (en) 2018-11-27

Similar Documents

Publication Publication Date Title
Zhang et al. A hierarchical game framework for resource management in fog computing
Chemodanov et al. A near optimal reliable composition approach for geo-distributed latency-sensitive service chains
CN107483355B (en) Data center-oriented online scene low-bandwidth overhead traffic scheduling scheme
CN114827021B (en) Multimedia service flow acceleration system based on SDN and machine learning
CN110234155A (en) A kind of super-intensive network insertion selection method based on improved TOPSIS
CN114071582A (en) Service chain deployment method and device for cloud-edge collaborative Internet of things
CN105119751A (en) Service evaluation and selection method based on environment real-time perceiving
CN106060145A (en) Profit based request access control method in distributed multi-cloud data center
CN107454009B (en) Data center-oriented offline scene low-bandwidth overhead traffic scheduling scheme
CN108833294B (en) Low-bandwidth-overhead flow scheduling method for data center wide area network
CN108833993B (en) Cost-sensitive network video distribution method
CN103188152A (en) Cognitive network quality of service (QoS) routing method based on service differentiation
Liao et al. Live: learning and inference for virtual network embedding
WO2023082431A1 (en) Traffic scheduling method and system under multi-square ring structure
CN112165721B (en) Multi-service task unloading and service migration method based on edge computing
CN108900315B (en) Service profit optimization method for cloud service provider
CN113032146A (en) Robust service supply method for multi-access edge computing environment
Cui et al. Multi-Agent Reinforcement Learning Based Cooperative Multitype Task Offloading Strategy for Internet of Vehicles in B5G/6G Network
CN102388585B (en) Network optimization flow control method, device and system
CN105207905A (en) Route selection method and device
CN107659501B (en) Efficiency optimized transmission method and system based on complicated gradient network
Gupta et al. Optimal network design: edge server placement and link capacity assignment for delay-constrained services
CN112700269A (en) Distributed data center selection method based on anisotropic reinforcement learning
Dong et al. More requests, less cost: uncertain inter-datacenter traffic transmission with multi-tier pricing
CN102957724B (en) A kind of dynamic delivery method relating to network and application thereof

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