WO2016178376A1 - 仮想ネットワーク制御装置、仮想ネットワーク制御方法、及びプログラム - Google Patents
仮想ネットワーク制御装置、仮想ネットワーク制御方法、及びプログラム Download PDFInfo
- Publication number
- WO2016178376A1 WO2016178376A1 PCT/JP2016/062772 JP2016062772W WO2016178376A1 WO 2016178376 A1 WO2016178376 A1 WO 2016178376A1 JP 2016062772 W JP2016062772 W JP 2016062772W WO 2016178376 A1 WO2016178376 A1 WO 2016178376A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- virtual network
- resource
- physical
- virtual
- network
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 230000004044 response Effects 0.000 claims abstract description 8
- 238000007726 management method Methods 0.000 claims description 49
- 238000005457 optimization Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 238000013468 resource allocation Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 230000004308 accommodation Effects 0.000 description 7
- 238000012546 transfer Methods 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- 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
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/76—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions
- H04L47/762—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions triggered by the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/82—Miscellaneous aspects
- H04L47/822—Collecting or measuring resource availability data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/83—Admission control; Resource allocation based on usage prediction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5019—Workload prediction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4641—Virtual LANs, VLANs, e.g. virtual private networks [VPN]
-
- 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
- H04L41/04—Network management architectures or arrangements
- H04L41/046—Network management architectures or arrangements comprising network management agents or mobile agents therefor
Definitions
- the present invention relates to a virtual network control technology, and in particular, to a request for construction of a virtual network including a computer resource required by the service provider and a communication performance required between the computer resources sent from the service provider.
- a technology for realizing resource allocation that meets the demands of many service providers in a virtual network operator that allocates resources on a physical network, while responding to situations where requests from each service provider change from moment to moment It is about.
- Non-Patent Document 1 With the progress of computer resource virtualization technology, it is possible to move a plurality of virtual computers to one computer (see Non-Patent Document 1).
- Live Migration that moves a system operating as a virtual computer to another computer without stopping the system on a physical computer is being promoted (non-patent literature). 2).
- Non-Patent Document 3 development of a technology for virtualizing a network is also underway (see Non-Patent Document 3), and it is possible to construct a plurality of virtual networks on a single physical network.
- Non-Patent Document 4 the virtual network operator who controls the virtual network will arrange the necessary virtual nodes and virtual resources so as to meet the demand from the service provider that provides the actual network service, and build the virtual network . Then, the constructed virtual network is provided to the service provider, and the service provider service is provided using the virtual network.
- Non-Patent Document 2 can be used to move a virtual node from a computer that currently accommodates it to another computer, Since the movement procedure includes the transfer of the image data of the virtual node, it places a heavy load on the network.
- Non-Patent Document 5 discusses a method for reconfiguring a virtual network in response to a change in the situation, but the reconfiguration considers only the demands observed at each time, and ad hoc reconfiguration There is a problem that has become. As a result, the movement of the virtual node frequently occurs, and there is a possibility that a large load is applied to the network.
- the present invention has been made in view of the above points, and an object of the present invention is to provide a technique for realizing virtual network control following environmental changes.
- a virtual network control apparatus that allocates a managed physical resource in response to a virtual network embedding request, A physical network resource management agent that manages the usage of resources on the physical network at each future time; A virtual network control agent arranged for each virtual network, The virtual network control agent is: A demand forecasting means for forecasting future demand in the corresponding virtual network; Based on the demand prediction result obtained by the demand prediction means and information on the utilization status of resources on the future physical network acquired from the physical network resource management agent, the virtual network will be used at each future time.
- a virtual network control device comprising: a used resource determining unit that calculates a physical resource to be processed and notifies the physical network resource management agent of information on the physical resource related to the calculation result.
- composition of a system concerning an embodiment of the invention. It is a structural example of the virtual network control apparatus which concerns on embodiment of this invention. It is a flowchart which shows operation
- the technology according to the present embodiment predicts demand fluctuation and uses the prediction result to calculate the allocation of resources to the virtual network that satisfies the demand of the virtual network accommodated on the physical network as much as possible. Are performed in a short time cycle by cooperation of agents in the virtual network control device. As a result, by changing the allocated resources of the virtual network while predicting the future, it is possible to reduce the load of moving virtual nodes, etc., and to follow fluctuations in demand in a short time by performing control at short intervals can do.
- a virtual network control device that assigns a physical resource under management in response to a virtual network embedding request from a service provider is provided.
- the virtual network control device is arranged corresponding to each virtual network and a physical network resource management agent that manages the usage status of resources on the physical network at each future time, and predicts future demand in the virtual network. Calculate the physical resources that the virtual network will use at each future time based on the prediction results and information on the usage status of the resources on the future physical network obtained from the physical network resource management agent.
- a virtual network control agent having a function of notifying the physical network resource management agent.
- each virtual network control agent calculates a physical resource to be used at each future time in the corresponding virtual network, notifies the physical network resource management agent of the calculation result, and executes the physical network resource management agent. Through this, information on resources that other virtual networks want to use at each future time is exchanged, and resources used by each virtual network are determined.
- each virtual network control agent the predicted result of demand at each future time of the corresponding virtual network, and the utilization status of physical network resources of other virtual networks at each future time.
- the virtual network at each time in the future Decides on the resources to use.
- the resource allocation for the future of the virtual network can be performed via the physical network resource management agent. Can be shared with other virtual network control agents. Then, at the next time, each virtual network control agent has information on future use resources of each shared virtual network and the demand of the virtual network predicted again (for example, the previous one with new observation data). If you have a prediction error or an unexpected environmental change, by repeating the recalculation of the virtual network resources used, It is possible to perform control while correcting the error, and it is possible to realize resource allocation to the virtual network following the fluctuation of demand.
- FIG. 1 shows a configuration example of a system in the present embodiment.
- a plurality of nodes 10 and 20 are connected to transfer devices 30 to 50, and the transfer devices are connected by links.
- Each node is, for example, a physical computer (computer), and each transfer device is, for example, a physical communication device, such as a router or a switch.
- each node a single or a plurality of virtual nodes (virtual machines) can be operated.
- the virtual machine 11 operates on the node 10
- the virtual machines 21 and 22 operate on the node 20.
- the system according to the present embodiment includes a network database 80, and the network configuration information and “resource information of each node and traffic information of each transfer device” used by each virtual network are the network database. Collected in 80.
- the system includes service control devices 60 and 70 corresponding to each service, and further includes a virtual network control device 100 and a setting device 90.
- Each service control device generates a virtual network embedding request corresponding to the corresponding service.
- the virtual network control device 100 receives a request for embedding a virtual network from the service control devices 60 and 70, acquires network configuration information, resource usage status and traffic information of each node of each virtual network from the network database 80, and each virtual network Determine node resources and network resources to be allocated. Based on the resource information to be assigned to each determined virtual network, the setting device 90 inputs settings for operating the virtual node to each node, and inputs settings for path / bandwidth limitation to each transfer device.
- FIG. 2 shows a configuration example of the virtual network control apparatus 100 in the present embodiment.
- the virtual network control apparatus 100 includes virtual network control agents 110, 120,..., And a physical network resource management agent 130.
- the virtual network control agent may be referred to as a “virtual network control unit”, and the physical network resource management agent may be referred to as a “physical network resource management unit”.
- the virtual network control agent 110 includes a demand prediction unit 111 and a use resource determination unit 112.
- Other virtual network control agents have the same configuration.
- the physical network resource management agent 130 has a resource status management unit 131. The outline of the operation of each functional unit will be described below.
- the physical network management agent 130 uses the resource status management unit 131 to manage the resources of the nodes arranged in the network and manage the usage status of each link at the future at each time. That is, the physical network management agent 130 includes storage means such as a memory, and stores information on these resources, information on usage status at each future time, and the like.
- the virtual network control agent is a functional unit deployed corresponding to each virtual network.
- a new virtual network management agent is generated. “Generating” means that, for example, a program corresponding to the virtual network management agent is started in the virtual network control device 100.
- the demand prediction unit 111 predicts the demand of the corresponding virtual network. Based on the demand predicted by the demand prediction unit 111 and the resource usage status of other virtual networks at each future time acquired from the physical network management agent 130, the usage resource determination unit 112 determines whether the corresponding virtual network is the future. Decide which resources to use. Then, by notifying the physical network resource management agent 130 of the resources to be used at each determined future time, the information on the resource usage status of each future virtual network possessed by the physical network resource management agent 130 is updated.
- FIG. 3 is a flowchart showing the operation of the virtual network control agent 110 in the virtual network control apparatus 100 of the present embodiment.
- an operation example of the virtual network control agent 110 will be described, but other virtual network control agents perform the same operation.
- the virtual network control agent 110 first acquires the current virtual network traffic information and the virtual node usage information (which can be referred to as observation data) from the network database 80 to obtain the current virtual network.
- the demand for (the virtual network of the service corresponding to the virtual network control agent 110) is grasped (step S101).
- the virtual network control agent 110 predicts the future demand of the virtual network based on the acquired demand information (step S102).
- the method of demand prediction is not limited to a specific method.
- an existing demand prediction method can be used.
- the virtual network control agent 110 acquires information on resources that other virtual networks are scheduled to use at each future time from the physical network management agent 130 (step S103).
- the virtual network control agent 110 demands more virtual networks in the future based on information on resources that other virtual networks plan to use in the future and prediction of demand for its own virtual network. Is calculated and a future resource use plan is calculated so that the number of virtual nodes that need to be moved at each time is minimized (step S104).
- the virtual network control agent 110 starts reservation and use of the resource at the next time, and informs the physical network management agent 130 of the resource use plan in the future. Thereafter, returning to the acquisition of demand information, the prediction is performed again, the latest use plan of the future resource of the other virtual network is acquired, and the use plan of the future resource is calculated again.
- each virtual network agent can perform control corresponding to the demand fluctuation while avoiding the load due to the movement of the virtual node by considering the future demand fluctuation.
- the end timing of the repetitive processing is arbitrary, but can be ended by an instruction from the user of the control device, for example.
- the virtual network control apparatus 100 can be realized, for example, by causing one or a plurality of computers to execute a program describing the processing content described in the present embodiment.
- the function of the virtual network control apparatus 100 is to execute a program corresponding to the process executed by the virtual network control apparatus 100 using hardware resources such as a CPU, memory, and hard disk built in the computer. Can be realized.
- the program can be recorded on a computer-readable recording medium (portable memory or the like), stored, or distributed. It is also possible to provide the program through a network such as the Internet or electronic mail.
- FIG. 4 is a diagram illustrating a hardware configuration example of the virtual network control device 100 according to the embodiment of the present invention.
- the virtual network control device 100 in FIG. 4 includes a drive device 150, an auxiliary storage device 152, a memory device 153, a CPU 154, an interface device 155, a display device 156, an input device 157, and the like that are mutually connected by a bus B. .
- the program for realizing the processing in the virtual network control device 100 is provided by a recording medium 151 such as a CD-ROM or a memory card, for example.
- a recording medium 151 such as a CD-ROM or a memory card
- the program is installed from the recording medium 151 into the auxiliary storage device 152 via the drive device 150.
- the program does not necessarily have to be installed from the recording medium 151, and may be downloaded from another computer via a network.
- the auxiliary storage device 152 stores the installed program and also stores necessary files and data.
- the memory device 153 reads the program from the auxiliary storage device 152 and stores it when there is an instruction to start the program.
- the CPU 154 realizes functions related to the virtual network control device 100 in accordance with a program stored in the memory device 153.
- the interface device 155 is used as an interface for connecting to a network.
- the display device 156 displays a GUI (Graphical User Interface) by a program.
- the input device 157 includes a keyboard and mouse, buttons, a touch panel, and the like, and is used to input various operation instructions.
- the virtual network control agent 110 solves this optimization problem, and the virtual node at each time (1, 2,... H) from time 1 to time H when the current control time is 0. And the location (accommodation location in the physical resource) of the link (virtual link) between the virtual nodes is determined.
- the virtual network control agent 110 will be described, other virtual network control agents perform the same processing.
- a set of nodes N p in the network, a set of links L p , and a set of paths P p on the physical network, which are information on the physical network, are given as inputs.
- Such information can be acquired from the network database 80.
- Each element p of the path set P p is represented as a set of links through which the path passes.
- the start node is n p start
- the end node is n p end
- G p, l is It is defined so that p is 1 when passing through the link l, and 0 otherwise.
- the total amount U n (t) of computing resources that can be provided at each time t is given to the virtual network, excluding the amount of resources reserved from other virtual networks.
- the resource amount reserved from another virtual network at each time t is input from the physical network resource management agent 130, and the other virtual network is obtained from the total resource amount of the node acquired from the network database 80. Can be obtained by removing the reserved resource amount from Also, for each link l ⁇ L p , the total amount of bandwidth B l (t) that can be provided at each time t is given to the virtual network, excluding the amount of resources reserved from other virtual networks. .
- the resource amount reserved from the other virtual network at each time t is input from the physical network resource management agent 130, and the entire resource amount of the link acquired from the network database 80 is used to calculate the resource amount from the other virtual network. It can be obtained by removing the reserved resource amount.
- a set N v of virtual nodes that need to be embedded and a set L v of virtual links are given.
- a virtual node v l start as a starting point
- a virtual node v l end as an end point
- a predicted value b ⁇ l (t) of the traffic amount flowing through the virtual link at time t are given.
- ⁇ (hat) indicating the predicted value is described not on the beginning of the character but on the right side of the character.
- a predicted value u ⁇ v (t) of a computing resource that the virtual node needs at time t is given.
- the predicted value b ⁇ l (t) of the traffic amount flowing through the virtual link and the predicted value u ⁇ v (t) of the computational resource required by the virtual node at time t are demands obtained in step S102 in FIG. It is a result of prediction.
- the above input is used to determine a physical node that accommodates the virtual node and a path that accommodates the virtual link (a transmission path including one or more physical links) at each time t.
- M v, n Node (t) is a variable that is 1 when the virtual node v is accommodated in the physical node n at time t, and is 0 otherwise, and the variable is the physical of the accommodation destination of the virtual node. It is defined as a variable that represents a node.
- M l, p Link (t) be a variable that is 1 if the virtual link 1 is accommodated in the path p at time t, and 0 otherwise, and that variable represents the virtual link accommodation path. Define as a variable.
- Mv , n Node (0) and M1 , p Link (0) are given according to the locations where virtual nodes and virtual links are accommodated during control.
- the cost for accommodating the virtual node v in the physical node n at time t is defined as C n, v (t).
- the following functions are given as objective functions.
- the first term is the sum of the costs at all times
- the second term is the cost for moving the virtual node
- w is a weight parameter.
- This objective function is an objective function whose objective is to minimize the sum of a value obtained by multiplying the first term by (1-w) and a value obtained by multiplying the second term by w.
- the first term is an example of an index related to the usage status of physical resources
- the second term is an example of an index related to a load related to resource allocation change at each time.
- W is a real number not less than 0 and not more than 1.
- the virtual network control agent 110 can avoid the necessity of moving a large number of virtual nodes while reducing the cost for embedding the virtual nodes at each time.
- the cost (C n, v (t)) is defined as a function that increases monotonically as the resource that can be provided by the physical node increases, thereby avoiding the use of a physical node that can provide a large amount of resources.
- selection of a node that has as few resources as possible can be promoted, and the number of physical nodes used for accommodating the virtual network can be suppressed.
- the virtual network control agent 110 searches for a solution within the range satisfying the following constraint conditions for this optimization problem.
- Constraint 1 All virtual nodes are accommodated in any physical node.
- Restriction condition 3 The virtual link is accommodated only in the path starting from the physical node in which the virtual node serving as the starting point of the virtual link is accommodated.
- Restriction condition 4 The virtual link is accommodated only in the path whose physical node in which the virtual node that is the end point of the virtual link is accommodated is the end point.
- Restriction 5 The computing resources required by the virtual nodes accommodated in each physical node are less than the computing resources that can be provided by the physical nodes.
- Restriction condition 6 The total amount of bandwidth required by the virtual link accommodated in each physical link is smaller than the bandwidth that can be provided by the physical link.
- the virtual network control agent 110 can calculate the location (physical node, path) that accommodates each virtual node and virtual link at each time from time 1 to time H by solving the above optimization problem. Then, the physical network resource management agent 130 notifies the physical network resource management agent 130 of the virtual network at each time up to a future time H by notifying the physical network resource management agent 130 of the calculated result and the predicted value of the required calculation resource / bandwidth.
- the other virtual network control agents can determine the resources to be used by the corresponding virtual network after taking into account the resources that the virtual network will use in the future. it can.
- the virtual network control agent 110 accommodates the virtual node in the physical node defined at time 1 out of the locations accommodating the virtual nodes / virtual links obtained as a result of the optimization problem, and is determined at time 1.
- the setting device 90 is notified of setting information for accommodating the virtual link in the path, and the setting device 90 inputs the setting to the corresponding device in the physical network.
- the demand is predicted again, and other virtual network control agents calculate the resources used. Then, after waiting for notifying the physical network resource management agent 130 of information on the future used resources, new usable resource information is acquired, and then calculation is performed again.
- each virtual network control agent calculates only the accommodation location of the virtual node / virtual link of the corresponding virtual network, so that the calculation time can be kept short, and in a short time period.
- the calculation of the virtual node / virtual link accommodation location can be repeated.
- new virtual network embedding requests and unexpected demand fluctuations occurred while controlling the load on virtual node movement in consideration of future fluctuations in demand. Cases can also be handled.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
将来の各時刻における物理ネットワーク上の資源の利用状況を管理する物理ネットワーク資源管理エージェントと、
各仮想ネットワークに対して配置される仮想ネットワーク制御エージェントと、を備え、
前記仮想ネットワーク制御エージェントは、
対応する仮想ネットワークにおける将来の需要の予測を行う需要予測手段と、
前記需要予測手段により得られた需要の予測結果と、前記物理ネットワーク資源管理エージェントから取得する将来の物理ネットワーク上の資源の利用状況の情報とに基づいて、前記仮想ネットワークが将来の各時刻において利用する物理資源を計算し、当該計算結果に係る物理資源の情報を前記物理ネットワーク資源管理エージェントに通知する利用資源決定手段と、を備える
ことを特徴とする仮想ネットワーク制御装置が提供される。
本実施の形態に係る技術は、需要の変動を予測し、その予測結果を用いながら、物理ネットワーク上に収容される仮想ネットワークの需要を可能な限り満たすような仮想ネットワークへの資源の割り当ての計算を、仮想ネットワーク制御装置内のエージェントの連携により、短い時間周期で行うものである。その結果、将来を予測しながら仮想ネットワークの割り当て資源の変更を行うことにより、仮想ノードの移動等の負荷を抑えることができ、短い周期で制御を行うことにより、需要の変動に短時間で追随することができる。
図1に本実施の形態におけるシステムの構成例を示す。図1に示すように、本実施の形態に係るシステムにおいて、複数のノード10、20が転送装置30~50に接続され、また、転送装置同士がリンクにより接続されている。
図2に、本実施の形態における仮想ネットワーク制御装置100の構成例を示す。図2に示すように、仮想ネットワーク制御装置100は、仮想ネットワーク制御エージェント110、120、...、及び物理ネットワーク資源管理エージェント130を有する。なお、仮想ネットワーク制御エージェントを「仮想ネットワーク制御部」と称し、物理ネットワーク資源管理エージェントを「物理ネットワーク資源管理部」と称してもよい。
以下に、仮想ネットワーク制御エージェント110における、将来にわたる資源の利用計画を計算する際に用いる最適化問題の一例について説明する。仮想ネットワーク制御エージェント110は、本最適化問題を解くことにより、制御を行う現在時刻を0とした場合における、時刻1から時刻Hまでの各時刻(1、2、...H)の仮想ノード、及び仮想ノード間のリンク(仮想リンク)の収容箇所(物理資源における収容箇所)を決める。なお、ここでは、仮想ネットワーク制御エージェント110について説明するが、他の仮想ネットワーク制御エージェントも同様の処理を行っている。
11、21、22 仮想マシン
30~50 転送装置
60、70 サービス制御装置
80 ネットワークデータベース
90 設定装置
100 仮想ネットワーク制御装置
110、120 仮想ネットワーク制御エージェント
111 需要予測部
112 利用資源決定部
130 物理ネットワーク資源管理エージェント
131 資源状況管理部
Claims (8)
- 仮想ネットワーク埋め込みの要求に対して、管理下の物理資源の割り当てを行う仮想ネットワーク制御装置であって、
将来の各時刻における物理ネットワーク上の資源の利用状況を管理する物理ネットワーク資源管理エージェントと、
各仮想ネットワークに対して配置される仮想ネットワーク制御エージェントと、を備え、
前記仮想ネットワーク制御エージェントは、
対応する仮想ネットワークにおける将来の需要の予測を行う需要予測手段と、
前記需要予測手段により得られた需要の予測結果と、前記物理ネットワーク資源管理エージェントから取得する将来の物理ネットワーク上の資源の利用状況の情報とに基づいて、前記仮想ネットワークが将来の各時刻において利用する物理資源を計算し、当該計算結果に係る物理資源の情報を前記物理ネットワーク資源管理エージェントに通知する利用資源決定手段と、を備える
ことを特徴とする仮想ネットワーク制御装置。 - 各仮想ネットワーク制御エージェントにおいて、対応する仮想ネットワークにおける将来の各時刻において利用する物理資源を計算し、前記物理ネットワーク資源管理エージェントに計算結果を通知し、当該物理ネットワーク資源管理エージェントを介して他の仮想ネットワークが将来の各時刻に利用することが予測される資源に関する情報を交換しながら、各仮想ネットワークが利用する資源の決定を行う
ことを特徴とする請求項1に記載の仮想ネットワーク制御装置。 - 前記利用資源決定手段は、
前記仮想ネットワークの需要の予測結果と、将来の各時刻における他の仮想ネットワークによる物理ネットワークの資源の利用状況とを入力とし、物理資源の利用状況に関する指標と、各時刻における資源の割り当て変更にかかる負荷に関する指標の重み付きの和を最小化する最適化問題を解くことにより、将来における各時刻において、当該仮想ネットワークが利用する資源を決定する
ことを特徴とする請求項1又は2に記載の仮想ネットワーク制御装置。 - 前記仮想ネットワーク制御エージェントにおいて、
前記利用資源決定手段が、前記計算結果に基づき、前記仮想ネットワークに対する次時刻の資源割り当てを行った後に、前記物理ネットワーク資源管理エージェントを介した将来の時刻の物理資源の利用状況を再度取得し、前記需要予測手段が、前記需要の予測結果を新たな観測データを元に修正し、前記利用資源決定手段が、前記再度取得した物理資源の利用状況と、前記修正された需要の予測結果とに基づいて、前記仮想ネットワークが将来の各時刻において利用する物理資源を計算する、という処理を繰り返し実行することにより、前記仮想ネットワークへの資源割り当てを行う
ことを特徴とする請求項1ないし3のうちいずれか1項に記載の仮想ネットワーク制御装置。 - 仮想ネットワーク埋め込みの要求に対して、管理下の物理資源の割り当てを行う仮想ネットワーク制御装置が実行する仮想ネットワーク制御方法であって、
前記仮想ネットワーク制御装置は、将来の各時刻における物理ネットワーク上の資源の利用状況を管理する物理ネットワーク資源管理エージェントと、各仮想ネットワークに対して配置される仮想ネットワーク制御エージェントと、を備え、
前記仮想ネットワーク制御エージェントが、対応する仮想ネットワークにおける将来の需要の予測を行う需要予測ステップと、
前記需要予測ステップにより得られた需要の予測結果と、前記物理ネットワーク資源管理エージェントから取得する将来の物理ネットワーク上の資源の利用状況の情報とに基づいて、前記仮想ネットワークが将来の各時刻において利用する物理資源を計算し、当該計算結果に係る物理資源の情報を前記物理ネットワーク資源管理エージェントに通知する利用資源決定ステップと、を備える
ことを特徴とする仮想ネットワーク制御方法。 - 各仮想ネットワーク制御エージェントにおいて、対応する仮想ネットワークにおける将来の各時刻において利用する物理資源を計算し、前記物理ネットワーク資源管理エージェントに計算結果を通知し、当該物理ネットワーク資源管理エージェントを介して他の仮想ネットワークが将来の各時刻に利用することが予測される資源に関する情報を交換しながら、各仮想ネットワークが利用する資源の決定を行う
ことを特徴とする請求項5に記載の仮想ネットワーク制御方法。 - 前記利用資源決定ステップにおいて、前記仮想ネットワーク制御エージェントは、
前記仮想ネットワークの需要の予測結果と、将来の各時刻における他の仮想ネットワークによる物理ネットワークの資源の利用状況とを入力とし、物理資源の利用状況に関する指標と、各時刻における資源の割り当て変更にかかる負荷に関する指標の重み付きの和を最小化する最適化問題を解くことにより、将来における各時刻において、当該仮想ネットワークが利用する資源を決定する
ことを特徴とする請求項5又は6に記載の仮想ネットワーク制御方法。 - コンピュータを、請求項1ないし4のうちいずれか1項に記載の仮想ネットワーク制御装置の各手段として機能させるためのプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017516589A JP6406633B2 (ja) | 2015-05-07 | 2016-04-22 | 仮想ネットワーク制御装置、仮想ネットワーク制御方法、及びプログラム |
US15/571,925 US10572311B2 (en) | 2015-05-07 | 2016-04-22 | Virtual network control apparatus, virtual network control method, and program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015095193 | 2015-05-07 | ||
JP2015-095193 | 2015-05-07 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016178376A1 true WO2016178376A1 (ja) | 2016-11-10 |
Family
ID=57217907
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/062772 WO2016178376A1 (ja) | 2015-05-07 | 2016-04-22 | 仮想ネットワーク制御装置、仮想ネットワーク制御方法、及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US10572311B2 (ja) |
JP (1) | JP6406633B2 (ja) |
WO (1) | WO2016178376A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109375997A (zh) * | 2018-09-28 | 2019-02-22 | 北京三快在线科技有限公司 | 一种处理网络资源的方法、装置、设备及可读存储介质 |
JP2020135688A (ja) * | 2019-02-25 | 2020-08-31 | 日本電信電話株式会社 | 需要予測装置、需要予測方法及びプログラム |
US10795711B2 (en) * | 2018-01-10 | 2020-10-06 | Vmware, Inc. | Predictive allocation of virtual desktop infrastructure computing resources |
JPWO2021044596A1 (ja) * | 2019-09-05 | 2021-03-11 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10986036B1 (en) * | 2019-11-01 | 2021-04-20 | Hon Lin Technology Co., Ltd. | Method and apparatus for orchestrating resources in multi-access edge computing (MEC) network |
CN111079981A (zh) * | 2019-11-25 | 2020-04-28 | 南京群顶科技有限公司 | 一种基于业务资源冗余量预测的节能减排方法 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012511292A (ja) * | 2008-12-10 | 2012-05-17 | エヌイーシー ヨーロッパ リミテッド | 基盤ネットワーク上で少なくとも1つの仮想ネットワークを動作させる方法および仮想ネットワーク環境 |
JP2013175810A (ja) * | 2012-02-23 | 2013-09-05 | Nippon Telegr & Teleph Corp <Ntt> | ネットワークのリソース管理装置 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8180604B2 (en) * | 2008-09-30 | 2012-05-15 | Hewlett-Packard Development Company, L.P. | Optimizing a prediction of resource usage of multiple applications in a virtual environment |
-
2016
- 2016-04-22 JP JP2017516589A patent/JP6406633B2/ja active Active
- 2016-04-22 US US15/571,925 patent/US10572311B2/en active Active
- 2016-04-22 WO PCT/JP2016/062772 patent/WO2016178376A1/ja active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012511292A (ja) * | 2008-12-10 | 2012-05-17 | エヌイーシー ヨーロッパ リミテッド | 基盤ネットワーク上で少なくとも1つの仮想ネットワークを動作させる方法および仮想ネットワーク環境 |
JP2013175810A (ja) * | 2012-02-23 | 2013-09-05 | Nippon Telegr & Teleph Corp <Ntt> | ネットワークのリソース管理装置 |
Non-Patent Citations (2)
Title |
---|
TAKAHIRO FUKUNO ET AL.: "Study of Placement of Virtual Service Resources Based on Link Load", IEICE TECHNICAL REPORT, vol. 114, no. 477, 23 February 2015 (2015-02-23), pages 281 - 284 * |
YUICHI OSHITA ET AL.: "Resource Optimization of Virtual Networks Based on Model Predictive Control", IEICE TECHNICAL REPORT, vol. 114, no. 253, 9 October 2014 (2014-10-09), pages 1 - 6 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10795711B2 (en) * | 2018-01-10 | 2020-10-06 | Vmware, Inc. | Predictive allocation of virtual desktop infrastructure computing resources |
CN109375997A (zh) * | 2018-09-28 | 2019-02-22 | 北京三快在线科技有限公司 | 一种处理网络资源的方法、装置、设备及可读存储介质 |
JP2020135688A (ja) * | 2019-02-25 | 2020-08-31 | 日本電信電話株式会社 | 需要予測装置、需要予測方法及びプログラム |
WO2020175162A1 (ja) * | 2019-02-25 | 2020-09-03 | 日本電信電話株式会社 | 需要予測装置、需要予測方法及びプログラム |
JP7167767B2 (ja) | 2019-02-25 | 2022-11-09 | 日本電信電話株式会社 | 需要予測装置、需要予測方法及びプログラム |
JPWO2021044596A1 (ja) * | 2019-09-05 | 2021-03-11 | ||
WO2021044596A1 (ja) * | 2019-09-05 | 2021-03-11 | 日本電信電話株式会社 | ネットワーク設計装置、ネットワーク設計方法、及びプログラム |
JP7283549B2 (ja) | 2019-09-05 | 2023-05-30 | 日本電信電話株式会社 | ネットワーク設計装置、ネットワーク設計方法、及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
US20180143864A1 (en) | 2018-05-24 |
JP6406633B2 (ja) | 2018-10-17 |
US10572311B2 (en) | 2020-02-25 |
JPWO2016178376A1 (ja) | 2017-10-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6406633B2 (ja) | 仮想ネットワーク制御装置、仮想ネットワーク制御方法、及びプログラム | |
Rejiba et al. | A survey on mobility-induced service migration in the fog, edge, and related computing paradigms | |
EP3637733B1 (en) | Load balancing engine, client, distributed computing system, and load balancing method | |
US8423646B2 (en) | Network-aware virtual machine migration in datacenters | |
JP5602851B2 (ja) | 最適ネットワーク・トポロジの識別を用いた分散データ処理システム内のジョブ・スケジューリングのための方法及びシステム | |
KR101471749B1 (ko) | 클라우드 서비스의 가상자원 할당을 위한 퍼지 로직 기반의 자원평가 장치 및 방법 | |
He et al. | Robust optimization model for primary and backup resource allocation in cloud providers | |
JPWO2014119719A1 (ja) | リソース制御システム、制御パターン生成装置、制御装置、リソース制御方法及びプログラム | |
KR101578177B1 (ko) | 클라우드 컴퓨팅 환경에서의 자원 이용률에 기초한 마이그레이션 방법 및 시스템 | |
JP2012199644A (ja) | 仮想ネットワーク管理システム、仮想ネットワーク管理方法および仮想ネットワーク管理用プログラム | |
KR20210128722A (ko) | 멀리 클라우드 서비스 플랫폼 장치 및 방법 | |
JP6586237B2 (ja) | リソース割当装置及びリソース割当方法 | |
Guha Roy et al. | Service aware resource management into cloudlets for data offloading towards IoT | |
Spinnewyn et al. | Resilient application placement for geo-distributed cloud networks | |
Babu et al. | Interference aware prediction mechanism for auto scaling in cloud | |
JP6325348B2 (ja) | 仮想マシン配置装置 | |
Ma et al. | Mobility-aware delay-sensitive service provisioning for mobile edge computing | |
JP6721921B2 (ja) | 設備設計装置、設備設計方法、及びプログラム | |
US9124508B2 (en) | Communication control device communication control system, communication control method and program | |
Sanchez-Navarro et al. | Advanced spatial network metrics for cognitive management of 5G networks | |
JP6586228B2 (ja) | 経路計算制御装置及び経路計算制御方法 | |
JP6232698B2 (ja) | ネットワークスイッチ装置、タスク移動方法、およびタスク移動プログラム | |
Inoue et al. | Noise-induced VNE method for software-defined infrastructure with uncertain delay behaviors | |
JP6191361B2 (ja) | 情報処理システム、情報処理システムの制御方法及び制御プログラム | |
Einziger et al. | Virtual Service Embedding with Time-Varying Load and Provable Guarantees |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16789512 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017516589 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15571925 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16789512 Country of ref document: EP Kind code of ref document: A1 |