CN115499512B - Efficient resource allocation method and system based on super-fusion cloud virtualization - Google Patents
Efficient resource allocation method and system based on super-fusion cloud virtualization Download PDFInfo
- Publication number
- CN115499512B CN115499512B CN202211444125.4A CN202211444125A CN115499512B CN 115499512 B CN115499512 B CN 115499512B CN 202211444125 A CN202211444125 A CN 202211444125A CN 115499512 B CN115499512 B CN 115499512B
- Authority
- CN
- China
- Prior art keywords
- virtual
- mapping
- physical
- resource
- cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- G06F9/5072—Grid computing
-
- 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
- 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
Abstract
The invention relates to the technical field of virtualized resource allocation, and discloses a virtualized resource efficient allocation method and system based on a hyper-converged cloud, wherein the method comprises the following steps: the virtual network receives and analyzes the current cloud virtual resource mapping request to form a virtual node sequence; mapping the virtual nodes in the virtual node sequence to physical nodes; solving the virtual link mapping target function by adopting an improved heuristic algorithm, and mapping the virtual link to a physical link; and dynamically determining the resource optimization adjustment time of the physical nodes according to the current quantity of the cloud virtual resource mapping requests, performing optimization adjustment on the mapping virtual resources, and performing mapping processing on the cloud virtual resource mapping requests which are currently received and are not successfully mapped. The invention realizes the mapping of the virtual network to the physical layer by utilizing the heuristic algorithm and the adaptation degree of the virtual nodes and the physical nodes, efficiently distributes the physical layer equipment resources to different virtual network users, and improves the utilization rate of the physical resources.
Description
Technical Field
The invention relates to the technical field of virtualized resource allocation, in particular to a virtualized resource efficient allocation method and system based on a hyper-converged cloud.
Background
With the continuous update of network technologies (such as 5G/6G, edge computing), network function virtualization and software defined networking become the main enabling technologies of the next generation network architecture, a super-fusion cloud platform abstracts different physical resources into resource pools and performs unified management, a novel architecture is constructed, and the problem of efficient and safe resource allocation is always a huge challenge faced by the novel architecture. If the resource allocation is unreasonable, the overall performance of the super-fusion cloud platform is affected by frequent cross-network resource interaction. Aiming at the problem, the patent provides a virtualized resource mapping method based on a super-fusion cloud platform, and efficient allocation of virtual resources based on the super-fusion cloud is realized.
Disclosure of Invention
In view of this, the invention provides a method for efficiently allocating virtualized resources based on a super-fusion cloud, and aims to 1) construct a mapping relationship between a physical node and a virtual node based on the adaptation degree of the physical node and the virtual node, further map the virtual node into the physical node, and solve a virtual link mapping objective function by using a heuristic algorithm, so as to implement a link mapping scheme with the minimum switching times of communication subnets and the highest link mapping profit, implement mapping from a virtual network to a physical layer, and obtain a virtual node sequence network structure containing requested resources, wherein a user can directly call the virtual node sequence network structure to allocate physical resources for a cloud virtual resource mapping request; 2) The method comprises the steps of dynamically determining the optimized adjustment time of physical node resources according to the number of current cloud virtual resource mapping requests, adopting a larger adjustment time interval when the cloud virtual resource mapping requests are increased, or else adopting a smaller adjustment time interval to realize the self-adaptive change of the adjustment time interval, wherein the dynamic change amplitude of the adjustment time interval is related to the preset time interval and the adjustment time interval determined last time, so that the phenomenon that the excessive change of the adjustment time interval causes the existence of more or less cloud virtual resource mapping requests for mapping processing, the computing resources of a virtual network are wasted, the congestion degree of the virtual network is calculated in real time, the mapping virtualized resources in the current super-fusion cloud platform are optimized and adjusted based on the congestion degree of the virtual network, and the mapping processing efficiency of the virtual network is improved.
In order to achieve the purpose, the invention provides a virtualized resource efficient allocation method based on a hyper-converged cloud, which comprises the following steps:
s1: initializing a virtual network and physical nodes, wherein the virtual nodes in the virtual network receive and analyze a current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request;
s2: mapping the virtual nodes in the virtual node sequence to physical nodes, and marking the cloud virtual resource mapping request as an unmapped cloud virtual resource mapping request if no effective physical node exists currently;
s3: constructing a virtual link mapping target function based on mapping profits, and mapping virtual links between adjacent virtual nodes to physical links by adopting an improved heuristic algorithm;
s4: dynamically determining the resource optimization adjustment time of the physical nodes according to the current quantity of the cloud virtual resource mapping requests;
s5: and optimizing and adjusting the mapping virtualization resources in the current super-fusion cloud platform at the time of optimizing and adjusting the resources of the physical nodes, mapping the cloud virtual resource mapping requests which are currently received and not successfully mapped, and allocating the physical resources for the cloud virtual resource mapping requests according to the mapping processing result.
As a further improvement of the method of the invention:
optionally, initializing the virtual network and the physical node in the step S1 includes:
constructing a super-convergence cloud platform architecture, wherein the super-convergence cloud platform architecture comprises a physical layer and a virtual network, the physical layer comprises a storage device, a computing terminal device and physical links among different devices, when a user sends a cloud virtual resource mapping request to the virtual network, the virtual network obtains a virtual node sequence network structure containing the requested resource by establishing mapping with the physical layer, and the user can directly call the virtual node sequence network structure to allocate physical resources for the cloud virtual resource mapping request;
in the embodiment of the present invention, the storage device is a device capable of storing data, and includes a computer, a server, and the like, and the computing terminal device is a computer, a server, and the like capable of executing computing operations;
initializing a virtual network, wherein the virtual network comprises a plurality of virtual nodes, and initializing physical nodes, the physical nodes are devices in a physical layer in a super-convergence cloud platform architecture, and the initialized physical nodes form a graph structure of the physical layer, wherein points in the graph structure are the physical nodes, and edges in the graph structure are communication links between the physical nodes.
Optionally, the receiving and analyzing, by the virtual node in the step S1, the current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request, includes:
the method comprises the steps that a virtual network receives a current cloud virtual resource mapping request, wherein the cloud virtual resource mapping request comprises a storage resource request and a computing resource request, the storage resource request comprises data volume to be stored, and the computing resource request comprises computing complexity;
the virtual network analyzes the cloud virtual resource mapping request to obtain a plurality of storage resource requests and computing resource requests, and distributes the plurality of resource requests obtained by analysis to different virtual nodes to form a virtual node sequence of the current cloud virtual resource mapping request.
Optionally, mapping the virtual nodes in the virtual node sequence to physical nodes in the step S2 includes:
the mapping process of the virtual node comprises the following steps:
s21: calculating the mapping capability of different current physical nodes, and for the physical nodes for storage, calculating the mapping capability power of the physical nodes for storage 1 Comprises the following steps:
wherein:
as in the physical nodeThe mapping capacity of the storage equipment, space is the storage capacity space of the storage equipment, and n represents that n virtual nodes are mapped to the physical node;
mapping capabilitiesLess than a storage thresholdAnd mapping capabilitiesLess than the calculated thresholdIf no effective physical node exists, the cloud virtual resource mapping request is marked as a cloud virtual resource mapping request which is not mapped successfully, and the mapping operation is terminated;
s22: for any virtual node in the virtual node sequenceWherein i represents a virtual nodeThe received resource request is the ith resource request obtained by resolving,,representing virtual nodesThe received resource request is a storage resource request,representing virtual nodesThe received resource request is a computing resource request;
s23: for any virtual node with j =1And analyzing the received resource request information, wherein the data volume to be stored in the resource request information isTraversing all physical nodes for storageComputing physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:
if physical nodeIf the residual storage space is less than the data amount to be stored, the physical node is enabledAnd virtual nodeThe degree of adaptation of (a) is null; physical node with highest adaptation degreeAs arbitrary virtual nodesMapping node of;
S24: for any virtual node with j =2For the received calculation request informationPerforming analysis, and calculating the complexity of the request informationTraversing all physical nodes used for computationComputing physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:
Optionally, the constructing a virtual link mapping objective function based on mapping benefits in the step S3 includes:
the mapping benefit mainly comprises link mapping benefit, and for any two continuous virtual nodesAndbetween which a virtual link is formedAnd the mapping physical nodes corresponding to the virtual nodes are respectivelyAndmapping the physical links formed between the physical nodes toThe virtual link mapping objective function is:
wherein:
m represents the total number of virtual nodes corresponding to the cloud virtual resource mapping request;
Optionally, the mapping, in the step S3, the virtual links between adjacent virtual nodes to the physical links by using an improved heuristic algorithm includes:
solving the mapping objective function of the virtual link by adopting an improved heuristic algorithm to obtain a physical link mapped by the virtual link, wherein the mapping process of the virtual link is as follows:
s31: performing explosion operation on the m physical nodes obtained by mapping to generate explosion sparks to surrounding links, wherein the physical nodesThe number of explosion sparks generated was:
wherein:
representing by physical nodesAs a physical link of the origin is,a function value representing a function of substituting the physical link into the virtual link mapping objective function;
Wherein:
representing a physical linkIn physical nodeThe next link intersection point that is the starting point,a physical link without link crossing;
s33: returning to the step S31 until a physical link L containing m physical nodes is obtained, and carrying out resource transportation on each physical node through the physical link;
and forming a virtual node sequence network structure containing the request resources by the physical links and the virtual links obtained by mapping, wherein a user can directly call the virtual node sequence network structure to allocate physical resources for the cloud virtual resource mapping request.
Optionally, the dynamically determining, according to the number of the current cloud virtual resource mapping requests in the step S4, a resource optimization adjustment time of the physical node includes:
the determination process of the physical node resource optimization adjustment moment comprises the following steps:
s41: calculating the current variation amplitude of the cloud virtual resource mapping request quantity:
Wherein:
the number of current cloud virtual resource mapping requests received for the virtual network;representing the quantity of received cloud virtual resource mapping requests after the last time of physical node resource optimization adjustment;
s42: determining the next time of the resource optimization adjustment of the physical node as t:
wherein:
the method indicates that when the quantity of the cloud virtual resource mapping requests is increased, the physical node resource optimization adjusts the time interval,indicating the adjustment time interval of the resource optimization adjustment of the physical node when the quantity of the cloud virtual resource mapping requests increases last time;
indicating that when the number of the cloud virtual resource mapping requests is reduced, the physical node resource optimization adjusts the time interval,and the adjustment time interval of the resource optimization adjustment of the physical node is represented when the quantity of the cloud virtual resource mapping requests is reduced last time. In the embodiment of the invention, when the cloud virtual resource mapping request is increased, a larger adjustment time interval is adopted, otherwise, a smaller adjustment time interval is adopted, the self-adaptive change of the adjustment time interval is realized, and the dynamic change amplitude of the adjustment time interval is related to the preset time interval and the adjustment time interval determined last time, so that the excessive change of the adjustment time interval is avoided, the mapping processing is carried out on more or less cloud virtual resource mapping requests, and the computing resources of a virtual network are wasted.
Optionally, in the step S5, performing optimization adjustment on the mapping virtualized resource in the current hyper-convergence cloud platform at the time of optimization adjustment of the physical node resource, and performing mapping processing on the cloud virtual resource mapping request that is currently received and that is not successfully mapped, includes:
performing optimization adjustment on mapping virtualization resources in the current super-convergence cloud platform at a physical node resource optimization adjustment time t, wherein the mapping virtualization resources are virtual node sequence network structures, when a cloud virtual resource mapping request is successfully processed, mapping between the virtual node sequence network structures and a physical layer is formed in a virtual network, and a user can directly call the virtual node sequence network structures so as to realize calling of resources in the physical layer;
the optimization and adjustment process comprises the following steps:
Wherein:
representing the current hyper-fusion cloudThe number of cloud virtual resource mapping requests that the virtual network is processing in the station,representing the number of virtual node sequence network structures which have completed resource mapping and wait to be deleted in the current super-fusion cloud platform when a user is inWhen the virtual node sequence network structure is not called in the time interval of (3), the virtual node sequence network structure is deleted from the virtual network and is positioned inThe un-called virtual node sequence network structure of the time interval is the virtual node sequence network structure waiting for deletion;
representing the average processing time length of the cloud virtual resource mapping request currently processed;
s52: when in useWhen the congestion value is larger than the preset congestion threshold value, optimizing and adjusting mapping virtualization resources in the super-fusion cloud platform, otherwise, ending the current optimizing and adjusting process;
s53: mapping the virtual node sequence network structure waiting for deletion to a storage node in a physical layer, deleting the virtual node sequence network structure waiting for deletion in the virtual network, and reducing the congestion degree of the virtual network;
s54: and mapping the cloud virtual resource mapping request which is currently received and is not successfully mapped, and allocating physical resources for the cloud virtual resource mapping request.
In order to solve the above problems, the present invention provides a system for efficiently allocating virtualized resources based on a super-converged cloud, the system comprising:
the virtual node mapping device is used for initializing a virtual network and physical nodes, the virtual nodes in the virtual network receive and analyze the current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request, the virtual nodes in the virtual node sequence are mapped to the physical nodes, and if no effective physical node exists at present, the cloud virtual resource mapping request is marked as a cloud virtual resource mapping request which is not mapped successfully;
the virtual link mapping device is used for constructing a virtual link mapping target function based on mapping income and mapping virtual links between adjacent virtual nodes to physical links by adopting an improved heuristic algorithm;
and the resource optimization and adjustment module is used for dynamically determining the physical node resource optimization and adjustment time according to the current cloud virtual resource mapping request quantity, performing optimization and adjustment on the mapping virtual resources in the current super-fusion cloud platform at the physical node resource optimization and adjustment time, performing mapping processing on the currently received cloud virtual resource mapping requests which are not mapped successfully and allocating physical resources to the cloud virtual resource mapping requests according to the mapping processing result.
Compared with the prior art, the invention provides a virtualized resource efficient allocation method based on a hyper-converged cloud, which has the following advantages:
firstly, the present solution provides a mapping method from a virtual network to a physical layer, in which a virtual node in a virtual node sequence is mapped to a physical node, and the mapping process of the virtual node is as follows: calculating the mapping capability of different physical nodes at present, and for the physical nodes for storage, calculating the mapping capability of the different physical nodesComprises the following steps:
wherein:for storage in physical nodesThe mapping capacity of the device, space is the storage capacity space of the storage device, and n represents that n virtual nodes are mapped to the physical node; for a physical node used for computation, its mapping capabilityIs the remaining CPU resource; mapping capabilitiesLess than a storage thresholdAnd mapping capabilitiesLess than the calculated thresholdIf no effective physical node exists, the cloud virtual resource mapping request is marked as a cloud virtual resource mapping request which is not mapped successfully, and the mapping operation is terminated; for any virtual node in the virtual node sequenceWherein i represents a virtual nodeThe received resource request is the ith resource request obtained by resolving,,representing virtual nodesThe received resource request is a storage resource request,representing virtual nodesThe received resource request is a computing resource request; for any virtual node with j =1And analyzing the received resource request information, wherein the data volume to be stored in the resource request information isTraversing all physical nodes for storageComputing physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:representing physical nodesThe remaining storage space of (a);representing physical nodesThe number of connected communication links;representing physical nodesA storage capacity space of (a); if physical nodeIf the residual storage space is less than the data amount to be stored, the physical node is enabledAnd virtual nodeIs empty; physical node with highest adaptation degreeAs arbitrary virtual nodesOf the mapping node(ii) a For any virtual node with j =2Analyzing the received calculation request information, wherein the calculation complexity in the calculation request information isTraversing all physical nodes used for computationComputing physicsNode pointAnd virtual nodeDegree of adaptation of:
Wherein:representing physical nodesThe remaining CPU resources; physical node with highest adaptation degreeAs arbitrary virtual nodesMapping node of. Constructing a virtual link mapping objective function based on mapping benefits, wherein the mapping benefits mainly comprise link mapping benefits, and for any two continuous virtual nodesAndbetween which a virtual link is formedAnd is deficiency ofThe mapping physical nodes corresponding to the pseudo-nodes are respectivelyAndmapping physical links formed between physical nodes toThe virtual link mapping objective function is:
wherein:representing a physical link;representing a physical linkThe remaining bandwidth of;representing a physical linkThe number of subnet switches; m represents the total number of virtual nodes corresponding to the cloud virtual resource mapping request;indicating the maximum number of subnet switches. And solving the virtual link mapping target function by adopting an improved heuristic algorithm to obtain a physical link mapped by the virtual link. According to the scheme, the mapping relation between the physical nodes and the virtual nodes is constructed based on the adaptation degree of the physical nodes and the virtual nodes, and then the virtual nodes are mapped to the physical nodesIn the nodes, a heuristic algorithm is utilized to solve the virtual link mapping objective function, a link mapping scheme with the minimum communication subnet switching times and the highest link mapping profit is realized, the mapping from the virtual network to the physical layer is realized, a virtual node sequence network structure containing the requested resources is obtained, and a user can directly call the virtual node sequence network structure to allocate the physical resources for the cloud virtual resource mapping request.
Meanwhile, the scheme provides a virtual network optimization method, which is used for optimizing the virtual network according to the number of the current cloud virtual resource mapping requests received by the virtual networkDynamically determining the optimal adjustment time of the physical node resources, wherein the determination process of the optimal adjustment time of the physical node resources comprises the following steps: calculating the current variation amplitude of the cloud virtual resource mapping request quantity:
Wherein:the number of current cloud virtual resource mapping requests received for the virtual network;representing the quantity of received cloud virtual resource mapping requests after the last time of physical node resource optimization adjustment; determining the next time of the resource optimization adjustment of the physical node as t:
wherein:representing the last time of resource optimization adjustment of the physical node;representing a preset physical node resource optimization adjustment time interval;indicating that when the quantity of the cloud virtual resource mapping requests is increased, the physical node resource optimization adjusts the time interval,indicating the adjustment time interval of the resource optimization adjustment of the physical node when the quantity of the cloud virtual resource mapping requests is increased last time;the resource optimization adjustment time interval of the physical node is adjusted when the number of the cloud virtual resource mapping requests is reduced,and the adjustment time interval of the resource optimization adjustment of the physical node is represented when the quantity of the cloud virtual resource mapping requests is reduced last time. Performing optimization adjustment on mapping virtualization resources in the current super-convergence cloud platform at a physical node resource optimization adjustment time t, wherein the mapping virtualization resources are virtual node sequence network structures, when a cloud virtual resource mapping request is successfully processed, mapping between the virtual node sequence network structures and a physical layer is formed in a virtual network, and a user can directly call the virtual node sequence network structures so as to realize calling of resources in the physical layer; wherein the optimization and adjustment process comprises: calculating congestion degree of virtual network in current super-convergence cloud platform:
Wherein:represents the number of cloud virtual resource mapping requests processed by the virtual network in the current super-convergence cloud platform,representing the number of virtual node sequence network structures which have completed resource mapping and wait to be deleted in the current super-fusion cloud platform when a user is inWhen the virtual node sequence network structure is not called in the time interval of (3), the virtual node sequence network structure is deleted from the virtual network and is positioned inThe non-called virtual node sequence network structure of the time interval is the virtual node sequence network structure waiting for deletion;representing the average processing time of the cloud virtual resource mapping request currently processed; when in useIf the congestion value is larger than the preset congestion threshold value, optimizing and adjusting the mapping virtualization resources in the super-fusion cloud platform, otherwise, ending the current optimizing and adjusting process; mapping the virtual node sequence network structure waiting for deletion to the storage nodes in the physical layer, and deleting the virtual nodes waiting for deletion in the virtual networkThe sequence network structure reduces the congestion degree of the virtual network; and mapping the cloud virtual resource mapping request which is currently received and is not successfully mapped, and allocating physical resources for the cloud virtual resource mapping request. According to the scheme, the optimized adjustment time of the physical node resources is dynamically determined according to the number of the current cloud virtual resource mapping requests, when the cloud virtual resource mapping requests are increased, a larger adjustment time interval is adopted, otherwise, a smaller adjustment time interval is adopted, the self-adaptive change of the adjustment time interval is realized, the dynamic change amplitude of the adjustment time interval is related to the preset time interval and the adjustment time interval determined last time, the excessive change of the adjustment time interval is avoided, the mapping processing of more or less cloud virtual resource mapping requests is avoided, the computing resources of a virtual network are wasted, the congestion degree of the virtual network is calculated in real time, the mapping virtualized resources in the current super-fusion cloud platform are optimized and adjusted based on the congestion degree of the virtual network, and the mapping processing efficiency of the virtual network is improved.
Drawings
Fig. 1 is a schematic flowchart of a virtualized resource efficient allocation method based on a hyper-converged cloud according to an embodiment of the present invention;
fig. 2 is a functional block diagram of a system for efficiently allocating resources based on a super-converged cloud virtualization according to an embodiment of the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a virtualized resource efficient allocation method based on a super-fusion cloud. The execution subject of the efficient resource allocation method based on the super-converged cloud includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the efficient resource allocation method based on the super-converged cloud may be executed by software or hardware installed in the terminal device or the server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
s1: initializing a virtual network and physical nodes, and receiving and analyzing a current cloud virtual resource mapping request by the virtual nodes in the virtual network to form a virtual node sequence based on the mapping request.
Initializing a virtual network and a physical node in the step S1 includes:
constructing a super-convergence cloud platform architecture, wherein the super-convergence cloud platform architecture comprises a physical layer and a virtual network, the physical layer comprises a storage device, a computing terminal device and physical links among different devices, when a user sends a cloud virtual resource mapping request to the virtual network, the virtual network obtains a virtual node sequence network structure containing the requested resource by establishing mapping with the physical layer, and the user can directly call the virtual node sequence network structure to allocate physical resources for the cloud virtual resource mapping request;
initializing a virtual network, wherein the virtual network comprises a plurality of virtual nodes, and initializing physical nodes, the physical nodes are devices in a physical layer in a super-convergence cloud platform architecture, and the initialized physical nodes form a graph structure of the physical layer, wherein points in the graph structure are the physical nodes, and edges in the graph structure are communication links between the physical nodes.
In the step S1, the virtual node receives and analyzes the current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request, including:
the method comprises the steps that a virtual network receives a current cloud virtual resource mapping request, wherein the cloud virtual resource mapping request comprises a storage resource request and a computing resource request, the storage resource request comprises data volume to be stored, and the computing resource request comprises computing complexity;
the virtual network analyzes the cloud virtual resource mapping request to obtain a plurality of storage resource requests and computing resource requests, and distributes the plurality of resource requests obtained by analysis to different virtual nodes to form a virtual node sequence of the current cloud virtual resource mapping request.
S2: and mapping the virtual nodes in the virtual node sequence to the physical nodes, and marking the cloud virtual resource mapping request as an unmapped cloud virtual resource mapping request if no effective physical node exists currently.
Mapping the virtual nodes in the virtual node sequence to physical nodes in the step S2 includes:
the mapping process of the virtual node comprises the following steps:
s21: calculating the mapping capability of different physical nodes at present, and for the physical nodes for storage, calculating the mapping capability of the different physical nodesComprises the following steps:
wherein:
the mapping capacity of the storage equipment in the physical node is shown, space is the storage capacity space of the storage equipment, and n represents that n virtual nodes are mapped to the physical node;
will map capabilitiesLess than a storage thresholdAnd mapping capabilitiesLess than the calculated thresholdIf no effective physical node exists, the cloud virtual resource mapping request is marked as a cloud virtual resource mapping request which is not mapped successfully, and the mapping operation is terminated;
s22: for any virtual node in the virtual node sequenceWherein i represents a virtual nodeReceived is the ith resource request obtained by parsing,,representing virtual nodesThe received resource request is a storage resource request,representing virtual nodesThe received resource request is a computing resource request;
s23: for any virtual node with j =1And analyzing the received resource request information, wherein the data volume to be stored in the resource request information isTraversing all physical nodes for storageCalculating physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:
if physical nodeIf the residual storage space is less than the data amount to be stored, the physical node is enabledAnd virtual nodeIs empty; physical node with highest adaptation degreeAs arbitrary virtual nodesOf the mapping node;
S24: for any virtual node with j =2Analyzing the received calculation request information, wherein the calculation complexity in the calculation request information isTraversing all physical nodes used for computationComputing physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:
S3: and constructing a virtual link mapping objective function based on the mapping profit, and mapping the virtual links between the adjacent virtual nodes to the physical links by adopting an improved heuristic algorithm.
The step S3 of constructing a virtual link mapping objective function based on the mapping benefit includes:
the mapping benefit mainly comprises link mapping benefit, and for any two continuous virtual nodesAndbetween which a virtual link is formedAnd the mapping physical nodes corresponding to the virtual nodes are respectivelyAndmapping physical links formed between physical nodes toThe virtual link mapping objective function is:
wherein:
m represents the total number of virtual nodes corresponding to the cloud virtual resource mapping request;
In the step S3, an improved heuristic algorithm is adopted to map the virtual links between the adjacent virtual nodes to the physical links, including:
solving the virtual link mapping objective function by adopting an improved heuristic algorithm, and solving to obtain a physical link mapped by the virtual link, wherein the mapping process of the virtual link is as follows:
s31: performing explosion operation on the m physical nodes obtained by mapping to generate explosion sparks to surrounding links, wherein the physical nodesThe number of explosion sparks generated is:
wherein:
representing by physical nodesAs a physical link of the origin is,a function value representing a function of substituting the physical link into the virtual link mapping objective function;
Wherein:
representing a physical linkIn the physical nodeThe next link intersection point that is the starting point,a physical link without link crossing;
s33: returning to the step S31 until a physical link L containing m physical nodes is obtained, and carrying out resource transportation on each physical node through the physical link;
and forming a virtual node sequence network structure containing the request resources by the physical links and the virtual links obtained by mapping, wherein a user can directly call the virtual node sequence network structure to allocate physical resources for the cloud virtual resource mapping request.
S4: and dynamically determining the resource optimization adjustment time of the physical nodes according to the current quantity of the cloud virtual resource mapping requests.
In the step S4, dynamically determining the physical node resource optimization adjustment time according to the current cloud virtual resource mapping request number, including:
the determination process of the physical node resource optimization adjustment moment comprises the following steps:
s41: calculating the current variation amplitude of the cloud virtual resource mapping request quantity:
Wherein:
the number of current cloud virtual resource mapping requests received for the virtual network;representing the quantity of received cloud virtual resource mapping requests after the last time of physical node resource optimization adjustment;
s42: determining the next time of the resource optimization adjustment of the physical node as t:
wherein:
indicating that when the quantity of the cloud virtual resource mapping requests is increased, the physical node resource optimization adjusts the time interval,indicating the adjustment time interval of the resource optimization adjustment of the physical node when the quantity of the cloud virtual resource mapping requests is increased last time;
indicating that when the number of the cloud virtual resource mapping requests is reduced, the physical node resource optimization adjusts the time interval,and the adjustment time interval of the resource optimization adjustment of the physical node is represented when the quantity of the cloud virtual resource mapping requests is reduced last time. In the embodiment of the invention, when the cloud virtual resource mapping request is increased, a larger adjustment time interval is adopted, otherwise, a smaller adjustment time interval is adopted, the self-adaptive change of the adjustment time interval is realized, the dynamic change amplitude of the adjustment time interval is related to the preset time interval and the last determined adjustment time interval, and the excessive change of the adjustment time interval is avoided, so that the existence of more or less cloud virtual resources is avoidedThe source mapping request is subjected to mapping processing, and computing resources of the virtual network are wasted.
S5: and performing optimization adjustment on the mapping virtualization resources in the current super-fusion cloud platform at the time of optimization adjustment of the physical node resources, performing mapping processing on the currently received and unsuccessfully mapped cloud virtual resource mapping requests, and allocating the physical resources for the cloud virtual resource mapping requests according to the mapping processing result.
In the step S5, the mapping virtualized resource in the current super-fusion cloud platform is optimally adjusted at the time of optimizing and adjusting the physical node resource, and the mapping processing is performed on the cloud virtual resource mapping request that is currently received and is not successfully mapped, including:
performing optimization adjustment on mapping virtualization resources in the current super-convergence cloud platform at a physical node resource optimization adjustment time t, wherein the mapping virtualization resources are virtual node sequence network structures, when a cloud virtual resource mapping request is successfully processed, mapping between the virtual node sequence network structures and a physical layer is formed in a virtual network, and a user can directly call the virtual node sequence network structures so as to realize calling of resources in the physical layer;
wherein the optimization and adjustment process comprises the following steps:
Wherein:
represents the number of cloud virtual resource mapping requests processed by the virtual network in the current super-convergence cloud platform,the number of virtual node sequence network structures which are used for representing that resource mapping is completed and deletion is waited in the current super-fusion cloud platform is performed when a user is inWhen the virtual node sequence network structure is not called in the time interval of (3), the virtual node sequence network structure is deleted from the virtual network and is positioned inThe un-called virtual node sequence network structure of the time interval is the virtual node sequence network structure waiting for deletion;
representing the average processing time of the cloud virtual resource mapping request currently processed;
s52: when the temperature is higher than the set temperatureIf the congestion value is larger than the preset congestion threshold value, optimizing and adjusting the mapping virtualization resources in the super-fusion cloud platform, otherwise, ending the current optimizing and adjusting process;
s53: mapping the virtual node sequence network structure waiting for deletion to a storage node in a physical layer, deleting the virtual node sequence network structure waiting for deletion in the virtual network, and reducing the congestion degree of the virtual network;
s54: and mapping the cloud virtual resource mapping request which is currently received and is not successfully mapped, and allocating physical resources for the cloud virtual resource mapping request.
Example 2:
as shown in fig. 2, a functional block diagram of a system for efficiently allocating resources based on a super-fusion cloud provided in an embodiment of the present invention is shown, which can implement the method for efficiently allocating resources based on a super-fusion cloud in embodiment 1.
The system 100 for efficiently allocating virtualized resources based on a super-converged cloud can be installed in electronic equipment. According to the realized functions, the system for efficiently allocating resources based on the super-fusion cloud virtualization can comprise a virtual node mapping device 101, a virtual link mapping device 102 and a resource optimization adjusting module 103. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and are stored in a memory of the electronic device.
The virtual node mapping device 101 is configured to initialize a virtual network and a physical node, where a virtual node in the virtual network receives and analyzes a current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request, maps the virtual node in the virtual node sequence to the physical node, and marks the cloud virtual resource mapping request as an unmapped cloud virtual resource mapping request if there is no valid physical node currently;
the virtual link mapping device 102 is configured to construct a virtual link mapping objective function based on mapping gains, and map virtual links between adjacent virtual nodes to physical links by using an improved heuristic algorithm;
the resource optimization and adjustment module 103 is configured to dynamically determine a physical node resource optimization and adjustment time according to the current cloud virtual resource mapping request number, perform optimization and adjustment on the mapping virtualization resources in the current hyper-converged cloud platform at the physical node resource optimization and adjustment time, perform mapping processing on currently received and unsuccessfully mapped cloud virtual resource mapping requests, and allocate physical resources to the cloud virtual resource mapping requests according to mapping processing results.
In detail, in the embodiment of the present invention, when the modules in the efficient resource allocation system 100 based on a super-fusion cloud are used, the same technical means as the efficient resource allocation method based on a super-fusion cloud described in fig. 1 are used, and the same technical effect can be produced, which is not described herein again.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of another identical element in a process, apparatus, article, or method comprising the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A virtualized resource efficient allocation method based on a super-converged cloud is characterized by comprising the following steps:
s1: initializing a virtual network and physical nodes, wherein the virtual nodes in the virtual network receive and analyze a current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request;
s2: mapping the virtual nodes in the virtual node sequence to physical nodes, and marking the cloud virtual resource mapping request as an unmapped cloud virtual resource mapping request if no effective physical node exists currently;
s3: constructing a virtual link mapping target function based on mapping profits, and mapping virtual links between adjacent virtual nodes to physical links by adopting an improved heuristic algorithm;
s4: dynamically determining the physical node resource optimization adjustment time according to the current cloud virtual resource mapping request quantity, wherein the method comprises the following steps:
the determination process of the physical node resource optimization adjustment moment comprises the following steps:
s41: calculating the current variation amplitude alpha of the cloud virtual resource mapping request quantity:
wherein:
mapping the number of requests for the current cloud virtual resource received by the virtual network;representing the quantity of cloud virtual resource mapping requests received after the last time of resource optimization adjustment of the physical nodes;
s42: determining the next time of the resource optimization adjustment of the physical node as t:
wherein:
indicating that when the quantity of the cloud virtual resource mapping requests is increased, the physical node resource optimization adjusts the time interval,indicating the adjustment time interval of the resource optimization adjustment of the physical node when the quantity of the cloud virtual resource mapping requests increases last time;
the resource optimization adjustment time interval of the physical node is adjusted when the number of the cloud virtual resource mapping requests is reduced,the adjustment time interval of the resource optimization adjustment of the physical node is represented when the quantity of the cloud virtual resource mapping requests is reduced last time;
s5: and optimizing and adjusting the mapping virtualization resources in the current super-fusion cloud platform at the time of optimizing and adjusting the resources of the physical nodes, mapping the cloud virtual resource mapping requests which are currently received and not successfully mapped, and allocating the physical resources for the cloud virtual resource mapping requests according to the mapping processing result.
2. The efficient resource allocation method based on the super-converged cloud virtualization according to claim 1, wherein initializing a virtual network and a physical node in the step S1 comprises:
constructing a super-convergence cloud platform architecture, wherein the super-convergence cloud platform architecture comprises a physical layer and a virtual network, the physical layer comprises a storage device, a computing terminal device and physical links among different devices, when a user sends a cloud virtual resource mapping request to the virtual network, the virtual network obtains a virtual node sequence network structure containing the requested resource by establishing mapping with the physical layer, and the user can directly call the virtual node sequence network structure to allocate physical resources for the cloud virtual resource mapping request;
initializing a virtual network, wherein the virtual network comprises a plurality of virtual nodes, and initializing physical nodes, the physical nodes are devices in a physical layer in a super-convergence cloud platform architecture, and the initialized physical nodes form a graph structure of the physical layer, wherein points in the graph structure are the physical nodes, and edges in the graph structure are communication links between the physical nodes.
3. The efficient allocation method for virtualized resources based on super-converged cloud according to claim 2, wherein the step S1, in which the virtual node receives and parses a current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request, includes:
the method comprises the steps that a virtual network receives a current cloud virtual resource mapping request, wherein the cloud virtual resource mapping request comprises a storage resource request and a computing resource request, the storage resource request comprises data volume to be stored, and the computing resource request comprises computing complexity;
the virtual network analyzes the cloud virtual resource mapping request to obtain a plurality of storage resource requests and computing resource requests, and distributes the plurality of resource requests obtained by analysis to different virtual nodes to form a virtual node sequence of the current cloud virtual resource mapping request.
4. The method for efficient resource allocation based on the super-converged cloud virtualization according to claim 3, wherein the mapping the virtual nodes in the virtual node sequence to the physical nodes in the step S2 includes:
the mapping process of the virtual node comprises the following steps:
s21: calculating the mapping capability of different current physical nodes, and for the physical nodes for storage, calculating the mapping capability of the different current physical nodesComprises the following steps:
wherein:
the mapping capacity of the storage equipment in the physical node is shown, space is the storage capacity space of the storage equipment, and n represents that n virtual nodes are mapped to the physical node;
mapping capabilitiesLess than a storage thresholdAnd mapping capabilitiesLess than the calculated thresholdIf no effective physical node exists, the cloud virtual resource mapping request is marked as a cloud virtual resource mapping request which is not mapped successfully, and the mapping operation is terminated;
s22: for any virtual node in the virtual node sequenceWherein i represents a virtual nodeReceived is the ith resource request obtained by parsing,,representing virtual nodesThe received resource request is a storage resource request,representing virtual nodesThe received resource request is a computing resource request;
s23: for theArbitrary virtual node ofAnalyzing the received resource request information to obtain the resource request informationThe amount of data to be stored in the source request information isTraversing all physical nodes for storageCalculating physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:
if the physical nodeIf the residual storage space is less than the data amount to be stored, the physical node is enabledAnd virtual nodeThe degree of adaptation of (a) is null; physical node with highest adaptation degreeAs arbitrary virtual nodesOf the mapping node;
S24: for theArbitrary virtual node ofAnalyzing the received calculation request information, and calculating the complexity of the calculation request information intoTraversing all physical nodes for computationCalculating physical nodesAnd virtual nodeDegree of adaptation of:
Wherein:
5. The method for efficient allocation of virtualized resources based on a super-converged cloud according to claim 1, wherein the step S3 of constructing a mapping objective function of the virtual link based on the mapping benefits comprises:
construction is based onA virtual link mapping objective function of mapping benefits, the mapping benefits mainly including link mapping benefits, for any two consecutive virtual nodesAndbetween which a virtual link is formedAnd the mapping physical nodes corresponding to the virtual nodes are respectivelyAndmapping physical links formed between physical nodes toSaid virtual link mapping an objective functionComprises the following steps:
wherein:
m represents the total number of virtual nodes corresponding to the cloud virtual resource mapping request;
6. The method for efficient resource allocation based on the super-converged cloud virtualization according to claim 5, wherein the mapping of the virtual links between the adjacent virtual nodes to the physical links by using an improved heuristic algorithm in the step S3 comprises:
solving the virtual link mapping objective function by adopting an improved heuristic algorithm, and solving to obtain a physical link mapped by the virtual link, wherein the mapping process of the virtual link is as follows:
s31: performing explosion operation on the m physical nodes obtained by mapping to generate explosion sparks to surrounding links, wherein the physical nodesThe number of explosion sparks generated is:
wherein:
representing by physical nodesAs a physical link of the origin is,a function value representing a function of substituting the physical link into the virtual link mapping objective function;
Wherein:
representing a physical linkIn physical nodeThe next link intersection point that is the starting point,a physical link for which no link crossing exists;
s33: returning to the step S31 until a physical link L containing m physical nodes is obtained, and carrying out resource transportation on each physical node through the physical link;
and forming a virtual node sequence network structure containing the request resource by the physical link and the virtual link obtained by mapping, wherein a user can directly call the virtual node sequence network structure to allocate physical resources for the cloud virtual resource mapping request.
7. The method according to claim 1, wherein the step S5 of performing optimization adjustment on the mapped virtualized resources in the current hyper-converged cloud platform at the time of optimization adjustment of the physical node resources, and performing mapping processing on the currently received cloud virtual resource mapping request and the cloud virtual resource mapping request that is not mapped successfully includes:
performing optimization adjustment on mapping virtualization resources in the current super-convergence cloud platform at a physical node resource optimization adjustment time t, wherein the mapping virtualization resources are virtual node sequence network structures, when a cloud virtual resource mapping request is successfully processed, mapping between the virtual node sequence network structures and a physical layer is formed in a virtual network, and a user can directly call the virtual node sequence network structures so as to realize calling of resources in the physical layer;
the optimization and adjustment process comprises the following steps:
Wherein:
represents the number of cloud virtual resource mapping requests processed by the virtual network in the current super-convergence cloud platform,representing the number of virtual node sequence network structures which have completed resource mapping and wait to be deleted in the current super-fusion cloud platform when a user is inWhen the virtual node sequence network structure is not called in the time interval, the virtual node sequence network structure is deleted from the virtual network and is positioned inThe non-called virtual node sequence network structure of the time interval is the virtual node sequence network structure waiting for deletion;
representing the average processing time of the cloud virtual resource mapping request currently processed;
s52: when in useWhen the congestion value is larger than the preset congestion threshold value, optimizing and adjusting mapping virtualization resources in the super-fusion cloud platform, otherwise, ending the current optimizing and adjusting process;
s53: mapping the virtual node sequence network structure waiting for deletion to a storage node in a physical layer, deleting the virtual node sequence network structure waiting for deletion in the virtual network, and reducing the congestion degree of the virtual network;
s54: and mapping the cloud virtual resource mapping request which is received currently and is not mapped successfully, and allocating physical resources to the cloud virtual resource mapping request.
8. A system for efficient allocation of virtualized resources based on a super-converged cloud, the system comprising:
the virtual node mapping device is used for initializing a virtual network and physical nodes, the virtual nodes in the virtual network receive and analyze the current cloud virtual resource mapping request to form a virtual node sequence based on the mapping request, the virtual nodes in the virtual node sequence are mapped to the physical nodes, and if no effective physical node exists at present, the cloud virtual resource mapping request is marked as a cloud virtual resource mapping request which is not mapped successfully;
the virtual link mapping device is used for constructing a virtual link mapping target function based on mapping income and mapping virtual links between adjacent virtual nodes to physical links by adopting an improved heuristic algorithm;
the resource optimization and adjustment module is used for dynamically determining physical node resource optimization and adjustment time according to the number of current cloud virtual resource mapping requests, performing optimization and adjustment on mapping virtual resources in a current super-fusion cloud platform at the physical node resource optimization and adjustment time, performing mapping processing on currently received cloud virtual resource mapping requests which are not mapped successfully, and allocating physical resources to the cloud virtual resource mapping requests according to mapping processing results, so that the super-fusion cloud virtual resource-based efficient allocation method is realized according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211444125.4A CN115499512B (en) | 2022-11-18 | 2022-11-18 | Efficient resource allocation method and system based on super-fusion cloud virtualization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211444125.4A CN115499512B (en) | 2022-11-18 | 2022-11-18 | Efficient resource allocation method and system based on super-fusion cloud virtualization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115499512A CN115499512A (en) | 2022-12-20 |
CN115499512B true CN115499512B (en) | 2023-01-17 |
Family
ID=84881093
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211444125.4A Active CN115499512B (en) | 2022-11-18 | 2022-11-18 | Efficient resource allocation method and system based on super-fusion cloud virtualization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115499512B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6442615B1 (en) * | 1997-10-23 | 2002-08-27 | Telefonaktiebolaget Lm Ericsson (Publ) | System for traffic data evaluation of real network with dynamic routing utilizing virtual network modelling |
CN101969391A (en) * | 2010-10-27 | 2011-02-09 | 北京邮电大学 | Cloud platform supporting fusion network service and operating method thereof |
CN109714219A (en) * | 2019-03-13 | 2019-05-03 | 大连大学 | A kind of virtual network function fast mapping algorithm based on satellite network |
EP3806389A1 (en) * | 2018-05-24 | 2021-04-14 | ZTE Corporation | Virtual subnet constructing method and device, and storage medium |
WO2022186808A1 (en) * | 2021-03-05 | 2022-09-09 | Havelsan Hava Elektronik San. Ve Tic. A.S. | Method for solving virtual network embedding problem in 5g and beyond networks with deep information maximization using multiple physical network structure |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6880002B2 (en) * | 2001-09-05 | 2005-04-12 | Surgient, Inc. | Virtualized logical server cloud providing non-deterministic allocation of logical attributes of logical servers to physical resources |
US7292585B1 (en) * | 2002-12-20 | 2007-11-06 | Symantec Operating Corporation | System and method for storing and utilizing routing information in a computer network |
US9015145B2 (en) * | 2006-12-22 | 2015-04-21 | Singapore Technologies Dynamics Ptd Ltd. | Method and apparatus for automatic configuration of meta-heuristic algorithms in a problem solving environment |
-
2022
- 2022-11-18 CN CN202211444125.4A patent/CN115499512B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6442615B1 (en) * | 1997-10-23 | 2002-08-27 | Telefonaktiebolaget Lm Ericsson (Publ) | System for traffic data evaluation of real network with dynamic routing utilizing virtual network modelling |
CN101969391A (en) * | 2010-10-27 | 2011-02-09 | 北京邮电大学 | Cloud platform supporting fusion network service and operating method thereof |
EP3806389A1 (en) * | 2018-05-24 | 2021-04-14 | ZTE Corporation | Virtual subnet constructing method and device, and storage medium |
CN109714219A (en) * | 2019-03-13 | 2019-05-03 | 大连大学 | A kind of virtual network function fast mapping algorithm based on satellite network |
WO2022186808A1 (en) * | 2021-03-05 | 2022-09-09 | Havelsan Hava Elektronik San. Ve Tic. A.S. | Method for solving virtual network embedding problem in 5g and beyond networks with deep information maximization using multiple physical network structure |
Non-Patent Citations (3)
Title |
---|
一种启发式网络虚拟化资源分配算法;罗娟等;《中国科学:信息科学》;20120820(第08期);全文 * |
云计算环境下基于拓扑感知的虚拟网络映射研究;陈春凯;《计算机应用与软件》;20141215(第12期);全文 * |
多控制器条件下区分QoS的虚拟SDN映射方法;赵志远等;《通信学报》;20170825(第08期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115499512A (en) | 2022-12-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7219121B2 (en) | Symmetrical multiprocessing in multiprocessor systems | |
US7765405B2 (en) | Receive side scaling with cryptographically secure hashing | |
CN110096362B (en) | Multitask unloading method based on edge server cooperation | |
CN107547746A (en) | Resource allocation method and related product | |
CN111163178B (en) | Game theory-based service deployment and task unloading method in edge computing | |
WO2019072162A1 (en) | Virtual network mapping method, device and storage medium | |
CN113708972A (en) | Service function chain deployment method and device, electronic equipment and storage medium | |
CN113835878A (en) | Resource allocation method and device, computer equipment and storage medium | |
CN111049903A (en) | Edge network load distribution algorithm based on application perception prediction | |
Liu et al. | VirtualEdge: Multi-domain resource orchestration and virtualization in cellular edge computing | |
CN113645076B (en) | Virtual network resource allocation method based on hypergraph matching algorithm | |
CN115499512B (en) | Efficient resource allocation method and system based on super-fusion cloud virtualization | |
CN115955685B (en) | Multi-agent cooperative routing method, equipment and computer storage medium | |
JP2012238084A (en) | Data load distribution arrangement system and data load distribution arrangement method | |
CN109462879B (en) | Admission control method and system | |
CN110308965B (en) | Rule-based heuristic virtual machine distribution method and system for cloud data center | |
CN112437449A (en) | Joint resource allocation method and area organizer | |
CN114780228B (en) | Hybrid cloud resource creation method and system | |
CN112685167A (en) | Resource using method, electronic device and computer program product | |
CN114298431A (en) | Network path selection method, device, equipment and storage medium | |
CN113377866A (en) | Load balancing method and device for virtualized database proxy service | |
Wang et al. | Advanced delay assured numerical heuristic modelling for peer to peer project management in cloud assisted internet of things platform | |
CN117251035B (en) | Heat dissipation control method, heat dissipation control device, electronic equipment and computer readable medium | |
CN112434805B (en) | Deep neural network module segmentation method | |
Han et al. | Approximation algorithm for the offloading problem in edge computing |
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 |