CN113014649B - Cloud Internet of things load balancing method, device and equipment based on deep learning - Google Patents
Cloud Internet of things load balancing method, device and equipment based on deep learning Download PDFInfo
- Publication number
- CN113014649B CN113014649B CN202110217510.4A CN202110217510A CN113014649B CN 113014649 B CN113014649 B CN 113014649B CN 202110217510 A CN202110217510 A CN 202110217510A CN 113014649 B CN113014649 B CN 113014649B
- Authority
- CN
- China
- Prior art keywords
- cloud
- load balancing
- data center
- things
- internet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1074—Peer-to-peer [P2P] networks for supporting data block transmission mechanisms
Abstract
The embodiment of the specification discloses a cloud Internet of things load balancing method, a cloud Internet of things load balancing device and cloud Internet of things load balancing equipment based on deep learning, wherein the method comprises the following steps: the cloud Internet of things application sends a resource application instruction to a cloud data center, and a resource application scheme is determined through a pre-trained cloud center global load balancing model; the cloud Internet of things application distributes a network between a cloud data center and a fog computing node according to a resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the cloud Internet of things application selects load balancing services according to the corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and the load balancing services are provided for the cloud Internet of things application; the cloud internet of things application determines resources of the cloud computing nodes or the cloud center meeting preset requirements through the load balancing service, and cloud internet of things load balancing is achieved. Through a cloud center global load balancing model, resources are reasonably distributed, and the pressure of a cloud data center is reduced.
Description
Technical Field
The specification relates to the field of internet of things, in particular to a cloud internet of things load balancing method, device and equipment based on deep learning.
Background
In recent years, cloud computing, internet of things and fog computing technologies are continuously integrated and developed, compared with the existing mature cloud computing, the fog computing forms a resource platform with a pipeline between a cloud and a terminal, a service platform is built on the side close to the network edge of a user, unified resources such as storage, computing and network are provided, and partial key service applications are sunk to the edge of an access network, so that the pressure of the cloud is reduced. On the other hand, with the arrival of the world of everything interconnection, massive devices need to be connected to the cloud, massive data can be generated, interaction between the intelligent device and the cloud is more frequent, and particularly, the device end of the internet of things needs to be kept in long connection to complete real-time interaction with the cloud.
Aiming at the application of the Internet of things, more reasonable balance service needs to be provided, and the pressure of a cloud data center is reduced.
Disclosure of Invention
One or more embodiments of the present specification provide a cloud-internet-of-things load balancing method, apparatus, and device based on deep learning, which are used to solve the following technical problems: aiming at the application of the Internet of things, more reasonable balance service needs to be provided, and the pressure of a cloud data center is reduced.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present specification provide a cloud internet of things load balancing method based on deep learning, where the method includes: the cloud Internet of things application sends a resource application instruction to a cloud data center, and a resource application scheme is determined through a pre-trained cloud center global load balancing model; the cloud Internet of things application distributes a network between a cloud data center and a fog computing node according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the cloud Internet of things application selects load balancing services according to the corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and the cloud Internet of things application is provided with the load balancing services; and the cloud Internet of things application determines resources of the fog computing nodes or the cloud center meeting preset requirements through the load balancing service, so that the cloud Internet of things load balancing is realized.
Further, the cloud internet of things application sends a resource application instruction to the cloud data center, and determines a resource application scheme through a pre-trained cloud center global load balancing model, and the method specifically includes the following steps: the cloud internet of things is applied to the cloud data center and sends a resource application instruction, and a resource application scheme is determined according to the resource requirement of the cloud internet of things application and the cloud center global load balancing model, wherein the resource application scheme comprises one or more of a resource condition, an elastic expansion requirement and a network connection condition.
Further, the cloud internet of things application selects a load balancing service according to the corresponding service network, so that the cloud data center distributes a predetermined cloud internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and the method specifically comprises the following steps: the cloud Internet of things application selects load balancing services according to a corresponding service network, so that the cloud data center determines a cloud Internet of things load balancing model conforming to the cloud Internet of things application according to a pre-trained general cloud Internet of things load balancing model and actual resource conditions of the cloud Internet of things application, and distributes the cloud Internet of things load balancing model conforming to the cloud Internet of things application to the corresponding cloud data center and the corresponding fog computing node.
Further, distributing the cloud internet of things load balancing model conforming to the cloud internet of things application to the corresponding cloud center and the corresponding fog computing node specifically comprises: and the cloud data center determines a plurality of load balancing service nodes according to the resource conditions of the corresponding cloud center and the corresponding fog computing nodes, and distributes the cloud Internet of things load balancing model which accords with the cloud Internet of things application to the corresponding load balancing service nodes.
Further, before the cloud internet of things application determines the resources of the cloud computing node or the cloud center meeting the preset requirements through the load balancing service, the method further includes: and the cloud data center determines a predictive load balancing strategy through the cloud Internet of things load balancing model conforming to the cloud Internet of things application, and issues the predictive load balancing strategy to the corresponding load balancing service node, so that the load balancing service node updates the cloud Internet of things load balancing model according to the load balancing service node.
Further, providing a load balancing service for the cloud and internet of things application specifically includes: and the load balancing service node of the cloud data center provides load balancing service for the cloud Internet of things application based on local service conditions and in combination with a corresponding cloud Internet of things load balancing model.
Further, before the cloud internet of things load balancing model conforming to the cloud internet of things application is distributed to the corresponding load balancing service node, the method further includes: and carrying out application analysis on the cloud Internet of things load balancing model conforming to the cloud Internet of things application so as to optimize the resource allocation of the load balancing service node.
Further, before determining the resource application scheme through a pre-trained cloud center global load balancing model, the method further includes: the cloud data center collects resource conditions of the cloud center and the fog computing nodes, and trains a cloud center global load balancing model based on the resource conditions of the cloud center and the fog computing nodes; the cloud data center collects resource conditions of the cloud center and the fog computing nodes, and optimizes the cloud center global load balancing model based on the resource conditions of the cloud center and the fog computing nodes.
One or more embodiments of the present specification provide a cloud internet of things load balancing apparatus based on deep learning, including: the sending unit is used for sending a resource application instruction by the cloud Internet of things application in the cloud data center and determining a resource application scheme through a pre-trained cloud center global load balancing model; the distribution unit is used for distributing a network between the cloud data center and the fog computing node by the cloud Internet of things application according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the selecting unit is used for selecting load balancing services according to the corresponding service network by the cloud Internet of things application, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and the load balancing services are provided for the cloud Internet of things application; and the determining unit is used for determining the resources of the cloud computing nodes or the cloud center meeting the preset requirements through the load balancing service by the cloud Internet of things application so as to realize cloud Internet of things load balancing.
One or more embodiments of the present specification provide a cloud internet of things load balancing device based on deep learning, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to: the cloud Internet of things application sends a resource application instruction to a cloud data center, and a resource application scheme is determined through a pre-trained cloud center global load balancing model; the cloud Internet of things application distributes a network between a cloud data center and a fog computing node according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the cloud Internet of things application selects load balancing services according to the corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and the cloud Internet of things application is provided with the load balancing services; and the cloud Internet of things application determines resources of the fog computing nodes or the cloud center meeting preset requirements through the load balancing service, so that cloud Internet of things load balancing is realized.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects: resources are reasonably distributed through a cloud center global load balancing model; in addition, a load balancing model which is in accordance with the cloud computing node is formed for the cloud computing node, and predictive load balancing under the application scene of the internet of things is achieved by combining the local resource condition, so that the business application requirements are completed more efficiently and reasonably, and the pressure of a cloud data center is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort. In the drawings:
fig. 1 is a schematic flowchart of a cloud-internet-of-things load balancing method based on deep learning according to one or more embodiments of the present disclosure;
fig. 2 is a schematic structural diagram of a cloud-internet-of-things load balancing apparatus based on deep learning according to one or more embodiments of the present disclosure;
fig. 3 is a schematic structural diagram of a cloud-internet-of-things load balancing device based on deep learning according to one or more embodiments of the present disclosure.
Detailed Description
The embodiment of the specification provides a cloud Internet of things load balancing method, device and equipment based on deep learning.
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present specification without any creative effort shall fall within the protection scope of the present specification.
With the rapid development of artificial intelligence technology, the algorithm evolution taking deep learning as the core and the super-strong evolutionary ability thereof, under the support of big data, a large-scale neural network similar to a human brain structure is obtained through training and construction, and various problems can be solved. Good application practice effects are achieved in a plurality of scenes through the neural network, the traditional mode recognition mode is broken through, and subversive changes are generated in all the theory fields.
In recent years, cloud computing, internet of things and fog computing technologies are continuously integrated and developed, compared with the existing mature cloud computing, the fog computing forms a resource platform with a pipeline between a cloud and a terminal, a service platform is built on the side close to the network edge of a user, unified resources such as storage, computing and network are provided, and partial key service applications are sunk to the edge of an access network, so that the pressure of the cloud is reduced. On the other hand, with the arrival of the world of everything interconnection, massive devices need to be connected to the cloud end, massive data can be generated, interaction between the intelligent device and the cloud end is more frequent, particularly, the device end of the internet of things needs to be kept in long connection, and real-time interaction with the cloud end is completed. Aiming at the application of the Internet of things, a new network computing architecture is added between a cloud application service and an equipment end, the service is distributed to the edge of a network closest to a user, the response speed of interaction is improved, and the traditional load balancing method cannot meet the requirement of a new scene to a certain extent. Under the circumstance, how to effectively utilize the deep learning technology and combine the characteristics of cloud internet of things application, the problem that how to more reasonably provide the load balancing service of the internet of things scene becomes urgent to solve becomes.
The embodiment of the specification provides a cloud Internet of things load balancing method, device and equipment based on deep learning, and aims to solve the technical problem of providing load balancing service of an Internet of things scene more reasonably by effectively utilizing a deep learning technology and combining the characteristics of cloud Internet of things application. The following description is made with reference to the accompanying drawings.
Fig. 1 is a flowchart of a cloud-internet-of-things load balancing method based on deep learning according to an embodiment of the present specification, and as shown in fig. 1, the cloud-internet-of-things load balancing method based on deep learning mainly includes the following steps:
and S101, the cloud Internet of things application sends a resource application instruction to the cloud data center, and a resource application scheme is determined through a pre-trained cloud center global load balancing model.
Further, in an embodiment of the present specification, the step S101 may specifically include:
the cloud internet of things application sends a resource application instruction to the cloud data center, and a resource application scheme is determined according to the resource requirement of the cloud internet of things application and the cloud center global load balancing model, wherein the resource application scheme comprises one or more of a resource condition, an elastic expansion requirement and a network connection condition.
In an embodiment of the present specification, a cloud internet of things application applies for resources in a cloud data center, and according to resource requirements such as a service scale, a data requirement, a computing requirement and the like provided by the cloud data center, a resource proposal application scheme is provided for the cloud internet of things application through a cloud center global load balancing model, where the resource application scheme includes a resource scale, a resource distribution condition, an elastic expansion requirement, a network connection condition and the like. It should be noted that a large amount of hardware resources are gathered by the cloud data centers, cloud infrastructure services and platform support services are provided for business applications, cross-cloud management and cooperation can be achieved through interaction among the cloud data centers, the cloud computing nodes are managed at the same time, and cloud internet of things application business is operated.
Before determining the resource application scheme through a pre-trained cloud center global load balancing model, the method further comprises: the cloud data center collects resource conditions of the cloud center and the fog computing nodes, and trains a cloud center global load balancing model based on the resource conditions of the cloud center and the fog computing nodes; the cloud data center collects resource conditions of the cloud center and the fog computing nodes, and optimizes the cloud center global load balancing model based on the resource conditions of the cloud center and the fog computing nodes.
In one embodiment of the present specification, before providing a resource proposal application scheme for a cloud internet of things application through a cloud-centric global load balancing model, the cloud-centric global load model needs to be trained and optimized. Specifically, the cloud data center collects historical data of the cloud center and the fog computing nodes, wherein the historical data comprises historical data of service application access conditions, resource utilization conditions and the like, massive historical data of the cloud center and the fog computing nodes are input into a cloud center global load balancing model, and the cloud center global load balancing model is trained; the cloud data center collects resource conditions of the cloud center and the fog computing nodes, and optimizes a cloud center global load balancing model based on the resource conditions of the cloud center and the fog computing nodes.
It should be noted that the cloud center global load balancing model is a neural network model mainly formed by combining a CNN convolutional neural network with an attention mechanism, and is combined with a conventional rule judgment model to realize load balancing of the service application system based on the global actual operating resource conditions of the cloud data center and the fog computing node. The cloud computing node is a resource node arranged on a pipeline between a cloud end and an equipment end, has strong computing and storage network capacity, is connected with a cloud data center, is uniformly managed by the cloud data center, pushes cloud service to the cloud computing node, and bears service and application running close to a user side.
In an embodiment of the present specification, the cloud data center divides resources into multiple resource types, such as data type resources, internet of things connection type resources, computing type resources, and network type resources, according to the characteristics of the cloud internet of things application.
In an embodiment of the present specification, a cloud center global load balancing model acquires resource data related to cloud internet of things application, inputs the acquired resource data related to the cloud internet of things application into the cloud internet of things load balancing model, and trains the cloud internet of things load balancing model. It should be noted that the cloud internet of things load balancing model is a model which is operated on a cloud data center or a fog computing node and mainly aims at the scene of the internet of things. The cloud-internet-of-things load balancing model is a neural network model formed based on a CNN convolutional neural network in combination with an attention mechanism and is formed in combination with a traditional rule model, different load balancing strategies are set by dividing service application scenes, equipment long connection loads and data service loads are separated according to the characteristic that internet-of-things equipment needs long connection, a more effective load balancing strategy is formed, and meanwhile, a targeted model is formed through training based on the characteristics of periodic access and position information of the internet of things.
And S102, the cloud Internet of things application distributes a network between the cloud data center and the fog computing node according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application.
In an embodiment of the present specification, after determining the resource application scheme, the cloud internet of things application allocates networks in the cloud data center, the cloud center and the fog computing node according to the resource application scheme, so as to construct a service network corresponding to the cloud internet of things application.
Step S103, selecting load balancing service by the cloud Internet of things application according to the corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and providing the load balancing service for the cloud Internet of things application.
Further, in an embodiment of the present specification, the step S103 may specifically include:
the cloud Internet of things application selects load balancing services according to a corresponding service network, so that the cloud data center determines a cloud Internet of things load balancing model conforming to the cloud Internet of things application according to a pre-trained general cloud Internet of things load balancing model and actual resource conditions of the cloud Internet of things application, and distributes the cloud Internet of things load balancing model conforming to the cloud Internet of things application to the corresponding cloud data center and the corresponding fog computing node.
In an embodiment of the present specification, the cloud internet of things application selects a load balancing service according to the corresponding service network in step S102, and the cloud data center generates a cloud internet of things load balancing model conforming to the cloud internet of things application for the cloud internet of things application according to a general cloud internet of things load balancing model and an actual resource situation of the cloud internet of things application. It should be noted that the load balancing service is mainly oriented to a cloud data center and a fog computing node, and provides an efficient load balancing function for cloud internet of things application through a service form.
In one embodiment of the present description, the cloud data center performs personalized optimization and distribution on the cloud internet of things load balancing model. Specifically, the cloud data center collects resource conditions of the cloud center and the fog computing nodes, optimizes the cloud internet of things load balancing model based on the resource conditions of the cloud center and the fog computing nodes, and distributes the optimized cloud internet of things load balancing model to the cloud center host and the fog computing nodes.
The distributing the cloud internet of things load balancing model conforming to the cloud internet of things application to the corresponding cloud center and the corresponding fog computing node specifically comprises: and the cloud data center determines a plurality of load balancing service nodes according to the resource conditions of the corresponding cloud center and the corresponding fog computing nodes, and distributes the cloud Internet of things load balancing model which accords with the cloud Internet of things application to the corresponding load balancing service nodes.
Specifically, the cloud data center forms a plurality of load balancing service nodes according to the physical environment of the cloud center corresponding to the cloud internet of things application, the resource condition of the fog computing nodes and the distribution condition of the resources. The cloud data center sends the cloud Internet of things load balancing model which accords with the cloud Internet of things application to the load balancing service node in advance through analyzing and judging the cloud Internet of things load balancing model of the cloud center and the fog computing node.
Before the cloud internet of things application determines the resources of the cloud computing nodes or the cloud center meeting the preset requirements through the load balancing service, the method further comprises the following steps: and the cloud data center determines a predictive load balancing strategy through the cloud Internet of things load balancing model conforming to the cloud Internet of things application, and issues the predictive load balancing strategy to the corresponding load balancing service node, so that the load balancing service node updates the cloud Internet of things load balancing model according to the load balancing service node.
Specifically, the cloud data center determines a predictive load balancing strategy according to a corresponding cloud internet of things load balancing model which accords with cloud internet of things application, and issues the predictive load balancing strategy to a corresponding load balancing service node. And the load balancing service node updates the cloud Internet of things load balancing model located at the load balancing service node according to the local cloud Internet of things load balancing model and in combination with a predictive load balancing strategy formed by the cloud data center.
The providing of the load balancing service for the cloud internet of things application specifically includes: and the load balancing service node of the cloud data center provides load balancing service for the cloud Internet of things application based on local service conditions and in combination with a corresponding cloud Internet of things load balancing model.
Specifically, the load balancing service node provides load balancing service for cloud internet of things application according to local service conditions and in combination with a local cloud internet of things load balancing model. It should be noted that log data of resources, traffic, access, and the like during the running period of the corresponding cloud internet of things application are continuously collected and aggregated to the cloud data center at the time of network idle. The cloud data center trains the corresponding cloud Internet of things load balancing model according to the actual operation data of the corresponding cloud Internet of things application to form a targeted model facing the cloud Internet of things application.
Before distributing the cloud internet of things load balancing model conforming to the cloud internet of things application to the corresponding load balancing service node, the method further comprises: and carrying out application analysis on the cloud Internet of things load balancing model conforming to the cloud Internet of things application so as to optimize the resource allocation of the load balancing service node.
Specifically, the cloud data center performs application analysis on a cloud internet of things load balancing model conforming to cloud internet of things application, optimizes resource allocation of the load balancing service node, and achieves personalized load balancing and improves resource utilization rate by distributing the cloud internet of things load balancing model.
And step S104, the cloud Internet of things application determines resources of the fog computing nodes or the cloud center meeting preset requirements through the load balancing service, so that the cloud Internet of things load balancing is realized.
In an embodiment of the description, the cloud internet of things application determines a resource meeting a preset requirement through a load balancing service, wherein the resource meeting the preset requirement is a resource of a fog computing node or a cloud center, and finally, the cloud internet of things load balancing is achieved.
Fig. 2 is a schematic structural diagram of a cloud-internet-of-things load balancing device based on deep learning according to an embodiment of the present disclosure. Cloud thing allies oneself with load balancing unit based on deep learning includes: the sending unit 202 is used for the cloud internet of things application to send a resource application instruction to the cloud data center, and a resource application scheme is determined through a pre-trained cloud center global load balancing model; the distribution unit 204 is used for distributing a network between the cloud data center and the fog computing node by the cloud internet of things application according to the resource application scheme so as to construct a service network corresponding to the cloud internet of things application; the selecting unit 206 is configured to select a load balancing service according to the corresponding service network by the cloud internet of things application, so that the cloud data center distributes a predetermined cloud internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and provides the load balancing service for the cloud internet of things application; the determining unit 208 is configured to determine, by the cloud internet of things application, resources of the cloud computing node or the cloud center that meet preset requirements through the load balancing service, so as to implement cloud internet of things load balancing.
Fig. 3 is a schematic structural diagram of a cloud-internet-of-things load balancing device based on deep learning according to an embodiment of the present specification, where the structural diagram includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to: the cloud Internet of things application sends a resource application instruction to a cloud data center, and a resource application scheme is determined through a pre-trained cloud center global load balancing model; the cloud Internet of things application distributes a network between a cloud data center and a fog computing node according to a resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the cloud Internet of things application selects load balancing services according to the corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud center and the corresponding fog computing node, and the load balancing services are provided for the cloud Internet of things application; the cloud internet of things application determines resources of the cloud computing nodes or the cloud center meeting preset requirements through the load balancing service, and cloud internet of things load balancing is achieved.
In the technical scheme provided by one or more embodiments of the specification, a cloud and internet of things load balancing method based on deep learning forms a load balancing model by utilizing a deep learning technology and combining a traditional rule judgment model, and trains the model according to massive cloud and internet of things application data; by adopting the main structure of the convolutional neural network of the attention mechanism, the service characteristics generated by the periodicity, the time sequence and the position attribute of the application service of the Internet of things can be better mined, and more reasonable predictive load balance is formed; in one or more embodiments of the present description, characteristics of an internet of things application are comprehensively considered, resources are divided into multiple resources such as data resources, internet of things connection resources, computing resources, network resources, and the like, a cloud internet of things service is combined, a south-oriented internet of things device connection service, a data acquisition service, an instruction issue service, a device management service, and a north-oriented application service are connected, different load strategies are adopted, a cloud data center and a cloud computing node adopt a unified planning service load balancing service, a targeted load balancing solution is formed through cloud-spanning collaboration and cloud-mist collaboration, overall resource allocation of the cloud internet of things service is improved, south-oriented service loads are pushed to an edge side closest to the service as much as possible, and processing efficiency is improved; aiming at the fog computing node, a model which accords with the use condition of local actual resources of the node is adopted, meanwhile, the model is linked with the cloud end, the local model is continuously optimized, an individualized predictive cloud internet of things load balancing model is formed aiming at specific cloud internet of things application, the business application requirements are completed more efficiently and reasonably, the pressure of a cloud data center is reduced, the business access efficiency and the user experience are improved, the resources are utilized more reasonably, and further the user cost is reduced.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.
Claims (9)
1. A cloud Internet of things load balancing method based on deep learning is characterized by comprising the following steps:
the cloud Internet of things application sends a resource application instruction to a cloud data center, and a resource application scheme is determined through a pre-trained cloud data center global load balancing model, wherein the resource application scheme comprises one or more of a resource condition, an elastic expansion requirement and a network connection condition;
before determining the resource application scheme through a pre-trained global load balancing model of the cloud data center, the method further comprises the following steps:
the cloud data center collects historical data of the cloud data center and the fog computing nodes, wherein the historical data comprises business application access conditions and resource utilization conditions;
inputting historical data of the cloud data center and the fog computing nodes into a global load balancing model of the cloud data center, and training the global load balancing model of the cloud data center;
the cloud data center collects resource conditions of the cloud data center and the fog computing nodes, and optimizes a global load balancing model of the cloud data center based on the resource conditions of the cloud data center and the fog computing nodes;
the cloud Internet of things application distributes a network between a cloud data center and a fog computing node according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the cloud Internet of things application selects a load balancing service according to a corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and the load balancing service is provided for the cloud Internet of things application;
the cloud internet of things application selects a load balancing service according to a corresponding service network so that the cloud data center distributes a predetermined cloud internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and the method specifically comprises the following steps:
the cloud Internet of things application selects load balancing services according to a corresponding service network, so that the cloud data center determines a cloud Internet of things load balancing model which accords with the cloud Internet of things application according to a pre-trained universal cloud Internet of things load balancing model and the actual resource condition of the cloud Internet of things application;
distributing the cloud Internet of things load balancing model conforming to the cloud Internet of things application to a corresponding cloud data center and a corresponding fog computing node;
and the cloud Internet of things application determines resources of the cloud computing nodes or the cloud data center meeting preset requirements through the load balancing service, so that the cloud Internet of things load balancing is realized.
2. The method according to claim 1, wherein the cloud-internet-of-things application sends a resource application instruction to the cloud data center, and determines a resource application scheme through a pre-trained global load balancing model of the cloud data center, specifically comprising:
the cloud internet of things application sends a resource application instruction to the cloud data center, and a resource application scheme is determined according to the resource requirement of the cloud internet of things application and the cloud data center global load balancing model.
3. The method according to claim 1, wherein the distributing the cloud internet of things load balancing model conforming to the cloud internet of things application to the corresponding cloud data center and the fog computing node specifically comprises:
and the cloud data center determines a plurality of load balancing service nodes according to the resource conditions of the corresponding cloud data center and the corresponding fog computing nodes, and distributes the cloud Internet of things load balancing model which accords with the cloud Internet of things application to the corresponding load balancing service nodes.
4. The method of claim 3, wherein before the cloud IOT application determines the resources of the cloud data center or the fog computing node that meet preset requirements through the load balancing service, the method further comprises:
and the cloud data center determines a predictive load balancing strategy through the cloud Internet of things load balancing model according with the cloud Internet of things application, and issues the predictive load balancing strategy to the corresponding load balancing service node, so that the load balancing service node updates the cloud Internet of things load balancing model according to the load balancing service node.
5. The method according to claim 3, wherein the providing the load balancing service to the cloud and internet of things application specifically comprises:
and the load balancing service node of the cloud data center provides load balancing service for the cloud Internet of things application based on local service conditions and in combination with a corresponding cloud Internet of things load balancing model.
6. The method according to claim 3, wherein before distributing the cloud IOT load balancing model conforming to the cloud IOT application to the corresponding load balancing service node, the method further comprises:
and carrying out application analysis on the cloud Internet of things load balancing model conforming to the cloud Internet of things application so as to optimize the resource allocation of the load balancing service node.
7. The method of claim 1, wherein before determining the resource application scenario through the pre-trained global load balancing model of the cloud data center, the method further comprises:
the cloud data center collects resource conditions of the cloud data center and the fog computing nodes, and trains a global load balancing model of the cloud data center based on the resource conditions of the cloud data center and the fog computing nodes;
the cloud data center collects resource conditions of the cloud data center and the fog computing nodes, and optimizes a global load balancing model of the cloud data center based on the resource conditions of the cloud data center and the fog computing nodes.
8. A cloud thing allies oneself with load balancing device based on deep learning includes:
the cloud data center resource application method comprises a sending unit, a resource application program and a resource application program, wherein the sending unit is used for sending a resource application instruction by a cloud internet of things application in the cloud data center and determining a resource application scheme through a pre-trained global load balancing model of the cloud data center, and the resource application scheme comprises one or more of a resource condition, an elastic expansion requirement and a network connection condition; before determining the resource application scheme through a pre-trained global load balancing model of the cloud data center, the method further comprises the following steps: the cloud data center collects historical data of the cloud data center and the fog computing nodes, wherein the historical data comprises business application access conditions and resource utilization conditions; historical data of the cloud data center and the fog computing nodes are input into a global load balancing model of the cloud data center, and the global load balancing model of the cloud data center is trained; the cloud data center collects resource conditions of the cloud data center and the fog computing nodes, and optimizes a global load balancing model of the cloud data center based on the resource conditions of the cloud data center and the fog computing nodes;
the distribution unit is used for distributing a network between the cloud data center and the fog computing node by the cloud Internet of things application according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application;
the selecting unit is used for selecting load balancing services according to the corresponding service network by the cloud internet of things application, so that the cloud data center distributes a predetermined cloud internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and providing the load balancing services for the cloud internet of things application, and the cloud internet of things application selects the load balancing services according to the corresponding service network, so that the cloud data center distributes the predetermined cloud internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and specifically comprises: the cloud Internet of things application selects load balancing services according to a corresponding service network, so that the cloud data center determines a cloud Internet of things load balancing model which accords with the cloud Internet of things application according to a pre-trained universal cloud Internet of things load balancing model and the actual resource condition of the cloud Internet of things application; distributing the cloud Internet of things load balancing model conforming to the cloud Internet of things application to a corresponding cloud data center and a corresponding fog computing node;
and the determining unit is used for determining the resources of the cloud computing nodes or the cloud data center which meet the preset requirements through the load balancing service by the cloud Internet of things application so as to realize cloud Internet of things load balancing.
9. A cloud thing allies oneself with load balancing equipment based on deep learning includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to:
the cloud Internet of things application sends a resource application instruction to a cloud data center, and a resource application scheme is determined through a pre-trained cloud data center global load balancing model, wherein the resource application scheme comprises one or more of a resource condition, an elastic expansion requirement and a network connection condition;
before determining the resource application scheme through a pre-trained global load balancing model of the cloud data center, the method further comprises the following steps:
the cloud data center collects historical data of the cloud data center and the fog computing nodes, wherein the historical data comprises business application access conditions and resource utilization conditions;
inputting historical data of the cloud data center and the fog computing nodes into a global load balancing model of the cloud data center, and training the global load balancing model of the cloud data center;
the cloud data center collects resource conditions of the cloud data center and the fog computing nodes, and optimizes a global load balancing model of the cloud data center based on the resource conditions of the cloud data center and the fog computing nodes;
the cloud Internet of things application distributes a network between a cloud data center and a fog computing node according to the resource application scheme so as to construct a service network corresponding to the cloud Internet of things application; the cloud Internet of things application selects a load balancing service according to a corresponding service network, so that the cloud data center distributes a predetermined cloud Internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and the load balancing service is provided for the cloud Internet of things application;
the cloud internet of things application selects a load balancing service according to a corresponding service network so that the cloud data center distributes a predetermined cloud internet of things load balancing model to the corresponding cloud data center and the corresponding fog computing node, and the method specifically comprises the following steps:
the cloud Internet of things application selects load balancing services according to a corresponding service network, so that the cloud data center determines a cloud Internet of things load balancing model which accords with the cloud Internet of things application according to a pre-trained universal cloud Internet of things load balancing model and the actual resource condition of the cloud Internet of things application;
distributing the cloud Internet of things load balancing model conforming to the cloud Internet of things application to a corresponding cloud data center and a corresponding fog computing node;
and the cloud Internet of things application determines resources of the cloud computing nodes or the cloud data center meeting preset requirements through the load balancing service, so that the cloud Internet of things load balancing is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110217510.4A CN113014649B (en) | 2021-02-26 | 2021-02-26 | Cloud Internet of things load balancing method, device and equipment based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110217510.4A CN113014649B (en) | 2021-02-26 | 2021-02-26 | Cloud Internet of things load balancing method, device and equipment based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113014649A CN113014649A (en) | 2021-06-22 |
| CN113014649B true CN113014649B (en) | 2022-07-12 |
Family
ID=76386306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110217510.4A Active CN113014649B (en) | 2021-02-26 | 2021-02-26 | Cloud Internet of things load balancing method, device and equipment based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113014649B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220391519A1 (en) * | 2021-06-04 | 2022-12-08 | International Business Machines Corporation | Data distribution and security in a multilayer storage infrastructure |
| CN115981876B (en) * | 2023-03-21 | 2023-06-16 | 国家体育总局体育信息中心 | Body-building data processing method, system and device based on cloud and fog architecture |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106161552A (en) * | 2015-04-16 | 2016-11-23 | 国家电网公司 | Load-balancing method and system under a kind of mass data environment |
| CN109831507A (en) * | 2019-02-14 | 2019-05-31 | 上海联寓智能科技有限公司 | Internet of Things system, load balancing method and storage medium |
| CN109947547A (en) * | 2019-03-14 | 2019-06-28 | 科学出版社成都有限责任公司 | Micro services architecting method based on cloud computing |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105282043A (en) * | 2014-06-20 | 2016-01-27 | 中国电信股份有限公司 | Global network load balancing system, device and method |
| CN104202254A (en) * | 2014-08-14 | 2014-12-10 | 江苏省邮电规划设计院有限责任公司 | An intelligent load balancing method based on a cloud calculation platform server |
| CN107172166B (en) * | 2017-05-27 | 2021-03-23 | 电子科技大学 | Cloud and mist computing system for industrial intelligent service |
| CN107766889B (en) * | 2017-10-26 | 2021-06-04 | 浪潮集团有限公司 | Cloud edge computing fused deep learning computing system and method |
| CN108540538B (en) * | 2018-03-20 | 2021-01-26 | 西安电子科技大学 | Cloud and mist combination networking application construction system based on SDN |
| CN108600355A (en) * | 2018-04-13 | 2018-09-28 | 济南浪潮高新科技投资发展有限公司 | A kind of mist computational load balance dispatching system and method |
| US11108849B2 (en) * | 2018-12-03 | 2021-08-31 | At&T Intellectual Property I, L.P. | Global internet of things (IOT) quality of service (QOS) realization through collaborative edge gateways |
| CN110417903B (en) * | 2019-08-01 | 2020-06-23 | 深圳风月科技有限公司 | Information processing method and system based on cloud computing |
| CN111124662B (en) * | 2019-11-07 | 2022-11-08 | 北京科技大学 | Fog calculation load balancing method and system |
| CN111444009B (en) * | 2019-11-15 | 2022-10-14 | 北京邮电大学 | Resource allocation method and device based on deep reinforcement learning |
| CN111813539A (en) * | 2020-05-29 | 2020-10-23 | 西安交通大学 | Edge computing resource allocation method based on priority and cooperation |
| CN112231075B (en) * | 2020-09-07 | 2023-09-01 | 武汉市九格合众科技有限责任公司 | Cloud service-based server cluster load balancing control method and system |
-
2021
- 2021-02-26 CN CN202110217510.4A patent/CN113014649B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106161552A (en) * | 2015-04-16 | 2016-11-23 | 国家电网公司 | Load-balancing method and system under a kind of mass data environment |
| CN109831507A (en) * | 2019-02-14 | 2019-05-31 | 上海联寓智能科技有限公司 | Internet of Things system, load balancing method and storage medium |
| CN109947547A (en) * | 2019-03-14 | 2019-06-28 | 科学出版社成都有限责任公司 | Micro services architecting method based on cloud computing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113014649A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Adaptive asynchronous federated learning in resource-constrained edge computing | |
| Xu et al. | Intelligent resource management in blockchain-based cloud datacenters | |
| Chen et al. | Deep reinforcement learning for computation offloading in mobile edge computing environment | |
| Zuo et al. | A multi-objective optimization scheduling method based on the ant colony algorithm in cloud computing | |
| Gu et al. | Cost minimization for big data processing in geo-distributed data centers | |
| CN108021451B (en) | Self-adaptive container migration method in fog computing environment | |
| CN104915407A (en) | Resource scheduling method under Hadoop-based multi-job environment | |
| CN108170530B (en) | Hadoop load balancing task scheduling method based on mixed element heuristic algorithm | |
| CN110389820B (en) | Private cloud task scheduling method for resource prediction based on v-TGRU model | |
| CN113014649B (en) | Cloud Internet of things load balancing method, device and equipment based on deep learning | |
| CN111930511A (en) | Identifier resolution node load balancing device based on machine learning | |
| TWI725744B (en) | Method for establishing system resource prediction and resource management model through multi-layer correlations | |
| Ghetas | A multi-objective Monarch Butterfly Algorithm for virtual machine placement in cloud computing | |
| Patni et al. | Load balancing strategies for grid computing | |
| Mansouri et al. | Hierarchical data replication strategy to improve performance in cloud computing | |
| CN113342510A (en) | Water and power basin emergency command cloud-side computing resource cooperative processing method | |
| Al-Jaroodi et al. | Service-oriented architecture for big data analytics in smart cities | |
| Jian et al. | A high-efficiency learning model for virtual machine placement in mobile edge computing | |
| Patil et al. | Memory and Resource Management for Mobile Platform in High Performance Computation Using Deep Learning | |
| CN114490049A (en) | Method and system for automatically allocating resources in containerized edge computing | |
| Huang et al. | Computation offloading for multimedia workflows with deadline constraints in cloudlet-based mobile cloud | |
| Hao et al. | Evaluation of nine heuristic algorithms with data‐intensive jobs and computing‐intensive jobs in a dynamic environment | |
| Devagnanam et al. | Design and development of exponential lion algorithm for optimal allocation of cluster resources in cloud | |
| Wang et al. | A resource allocation strategy for edge services based on intelligent prediction | |
| Tang et al. | Edge computing energy-efficient resource scheduling based on deep reinforcement learning and imitation learning |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220623 Address after: 250101 building S02, 1036 Chaochao Road, high tech Zone, Jinan City, Shandong Province Applicant after: Shandong Inspur Scientific Research Institute Co.,Ltd. Address before: Floor 6, Chaochao Road, Shandong Province Applicant before: JINAN INSPUR HIGH-TECH TECHNOLOGY DEVELOPMENT Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210622 Assignee: INSPUR SOFTWARE Co.,Ltd. Assignor: Shandong Inspur Scientific Research Institute Co.,Ltd. Contract record no.: X2023980030294 Denomination of invention: A method, device and device for load balancing of cloud IOT based on deep learning Granted publication date: 20220712 License type: Exclusive License Record date: 20230110 |