Iot node configuration method, apparatus, device, and storage medium

Abstract

The application discloses an Internet of Things node configuration method and device, equipment and a storage medium, and relates to the technical field of Internet of Things. The method comprises the following steps: constructing a disassembled matrix of a target node, wherein the disassembled matrix is used for representing the influence information of the target node on the quality of service of multiple applications in the Internet of Things under different network configurations, and the network configurations comprise any one of multiple traffic controls, resource expansions and instance expansions; performing calculation on the disassembled matrix of the target node to obtain a target solution set of the target node, wherein the target solution set comprises multiple solutions, the fitness of the multiple solutions in the target solution set satisfies a preset rule, and different solutions correspond to different network configuration information of the target node; calculating the cost overhead of each solution in the target solution set according to a preset cost overhead model; and configuring the target node according to the network configuration information corresponding to the target solution, wherein the target solution is a solution corresponding to the minimum cost overhead in the target solution set.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of Internet of Things, and particularly relates to an Internet of Things node configuration method and device, equipment and a storage medium. BACKGROUND

[0002] Internet of Things (IoT) refers to a network system in which various physical devices, sensors, actuators, etc. are connected through the Internet to realize mutual communication and data exchange. In the Internet of Things, a node refers to a device or sensor in the network, which can be various physical devices, terminal devices, sensors, actuators, etc. The node plays a role of data collection, transmission and processing in the network. When a traffic surge occurs in the Internet of Things, due to the limited computing and storage resources in the node, congestion of the node will occur, resulting in that the Quality of Service (QoS) requirement cannot be met. Although the prior art can increase the resource allocation of the congested node, so that the IoT application running on the node can obtain sufficient resources to meet the QoS requirement of the Internet of Things application, it will lead to an increase in the configuration cost of the Internet of Things, especially when the devices connected by the Internet of Things platform are measured in the order of billions, the cost overhead is often unacceptable. SUMMARY

[0003] The embodiments of the present application provide an Internet of Things node configuration method, device, equipment and storage medium, which can meet the service quality requirement while reducing the configuration cost of the Internet of Things.

[0004] In a first aspect, the embodiments of the present application provide an Internet of Things node configuration method, which comprises:

[0005] Constructing a disassembled matrix of a target node, the disassembled matrix being used to represent service quality influence information of the target node on a plurality of applications in the Internet of Things under different network configurations, the network configurations including any one of a plurality of traffic controls, resource expansions and instance expansions;

[0006] Calculating the disassembled matrix of the target node to obtain a target solution set of the target node, the target solution set including a plurality of solutions, the fitness of the plurality of solutions in the target solution set satisfying a preset rule, and different solutions corresponding to different network configuration information of the target node;

[0007] According to a preset cost overhead model, calculating the cost overhead of each solution in the target solution set;

[0008] According to the network configuration information corresponding to the target solution, configuring the target node, the target solution being a solution corresponding to the minimum cost overhead in the target solution set.

[0009] In a second aspect, the embodiments of the present application provide a device for configuring an Internet of Things node, the device comprising:

[0010] a construction module configured to construct a disassembled matrix of the target node, the disassembled matrix being used to represent service quality influence information of the target node on a plurality of applications in the Internet of Things under different network configurations, the network configurations including any one of a plurality of traffic controls, resource expansions and instance expansions;

[0011] a first calculation module configured to calculate the disassembled matrix of the target node to obtain a target solution set of the target node, the target solution set including a plurality of solutions, fitness of the plurality of solutions in the target solution set satisfying a preset rule, and different solutions corresponding to different network configuration information of the target node;

[0012] a second calculation module configured to calculate cost overhead of each solution in the target solution set according to a preset cost overhead model;

[0013] a configuration module configured to configure the target node according to network configuration information corresponding to a target solution, the target solution being a solution corresponding to minimum cost overhead in the target solution set.

[0014] In a third aspect, the embodiments of the present application provide an electronic device, the device comprising a processor and a memory storing computer program instructions; the processor implements the method for configuring an Internet of Things node as described in any one of the above aspects when executing the computer program instructions.

[0015] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, the computer readable storage medium storing computer program instructions, the computer program instructions being executed by a processor to implement the method for configuring an Internet of Things node as described in any one of the above aspects.

[0016] In a fifth aspect, the embodiments of the present application provide a computer program product, instructions in the computer program product being executed by a processor of an electronic device to cause the electronic device to perform the method for configuring an Internet of Things node as described in any one of the above aspects.

[0017] The Internet of Things node configuration method, device and equipment and storage medium provided by the embodiments of the present application can construct a disassembled matrix of a target node, the disassembled matrix is used to represent the service quality influence information of the target node on multiple applications in the Internet of Things under different network configurations, the network configurations include any one of multiple traffic control, resource expansion and instance expansion; the disassembled matrix of the target node is calculated to obtain a target solution set of the target node, the target solution set includes multiple solutions, the fitness of the multiple solutions in the target solution set meets a preset rule, and different solutions correspond to different network configuration information of the target node; the cost overhead of each solution in the target solution set is calculated according to a preset cost overhead model; and the target node is configured according to the network configuration information corresponding to the target solution, the target solution being the solution corresponding to the minimum cost overhead in the target solution set. In this way, the embodiments of the present application can first calculate the disassembled matrix of the target node with congestion to obtain a target solution set including multiple solutions, different solutions correspond to different network configuration information, then calculate the cost overhead of each solution in the target solution set according to a preset cost overhead model, and finally configure the target node according to the network configuration information corresponding to the solution with the minimum cost overhead, compared with the prior art which only increases resource configuration, the target node can be configured by the network configuration information corresponding to the minimum cost overhead in multiple network configurations, so that the service quality requirement is met while the configuration cost overhead of the Internet of Things is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced below. Those skilled in the art can also obtain other drawings according to these drawings without creating any creative labor.

[0019] Figure 1 is a flowchart of the Internet of Things node configuration method provided by the embodiments of the present application;

[0020] Figure 2 is a flowchart of a scene embodiment provided by the embodiments of the present application;

[0021] Figure 3 is a schematic diagram of a chromosome structure provided by the embodiments of the present application;

[0022] Figure 4 is a structural schematic diagram of the Internet of Things node configuration device provided by the embodiments of the present application;

[0023] Figure 5 is a structural schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0024] The features and exemplary embodiments of the various aspects of the present application will be described in detail below with reference to the drawings. For the purpose of clarity, the description is divided into the following sections: technical scheme, technical effects, and specific embodiments. The specific embodiments described herein are merely intended to explain the present application, and not to limit the present application. The present application can be implemented without some of the specific details described below. The following description of the embodiments is merely intended to provide a better understanding of the present application by showing examples of the present application.

[0025] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by an "includes" statement does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0026] Internet of Things (IoT) refers to a network system that connects various physical devices, sensors, actuators, etc. through the Internet to realize mutual communication and data exchange. In the Internet of Things, a node refers to a device or sensor in the network, which can be various physical devices, terminal devices, sensors, actuators, etc. The node plays the role of data collection, transmission and processing in the network. When a traffic surge occurs in the Internet of Things, due to the limited computing and storage resources in the node, congestion of the node will occur, resulting in the inability to meet the Quality of Service (QoS) requirements. Although the prior art can increase the resource allocation of the congested node, so that the IoT application running on the node can obtain sufficient resources to meet the QoS requirements of the Internet of Things application, it will lead to an increase in the configuration cost of the Internet of Things, especially when the devices connected by the Internet of Things platform are measured in the order of billions, the cost overhead is often unacceptable.

[0027] Professional terms:

[0028] 1. VNF: Virtualized Network Functions, which provides network functions in a network constructed by NFV technology.

[0029] 2. TCF: Traffic Control Function. The communication between nodes in the IoT platform is stateless, so that the traffic control function can be inserted without affecting the upper-layer IoT application. In this context, the proposal considers the traffic control at the network layer, and needs to be adjusted according to the traffic of the IoT. The QoS is managed by dynamically implementing and distributing enough TCFs on the nodes of the NIP.

[0030] 3. ANF: Application Network Function. In order to fully support the deployment of TCF, while considering that the IoT edge devices are generally small and it is very difficult to carry multiple VNFs, the proposal considers packaging the network functions into software components that can be dynamically deployed on the nodes of the IoT platform using the NFV architecture (NFV-enabled IoT Platform, NIP). Such software components are referred to as application network functions. Similarly to the fact that multiple VNFs can form a service function chain, multiple ANFs can also be concatenated to form a service function chain, thus providing an end-to-end network service.

[0031] In order to solve the problems of the prior art, the embodiments of the present application provide an IoT node configuration method, device and equipment, and a storage medium. First, the IoT node configuration method provided by the embodiments of the present application is introduced.

[0032] Figure 1 A flowchart of the IoT node configuration method provided by an embodiment of the present application is shown. As shown in Figure 1 The IoT node configuration method can include the following steps S101-S104:

[0033] S101, a disassembled matrix of a target node is constructed, the disassembled matrix is used to represent the service quality influence information of the target node on multiple applications in the IoT under different network configurations, and the network configurations include any one of multiple traffic control, resource expansion and instance expansion;

[0034] S102, the disassembled matrix of the target node is calculated to obtain a target solution set of the target node, the target solution set includes multiple solutions, the fitness of the multiple solutions in the target solution set meets a preset rule, and different solutions correspond to different network configuration information of the target node;

[0035] S103, the cost overhead of each solution in the target solution set is calculated according to a preset cost overhead model;

[0036] S104, the target node is configured according to the network configuration information corresponding to the target solution, and the target solution is a solution corresponding to the minimum cost overhead in the target solution set.

[0037] The Internet of Things node configuration method of the embodiments of the present application can construct a disassembled matrix of the target node, the disassembled matrix being used to represent the service quality influence information of the target node on multiple applications in the Internet of Things under different network configurations, the network configurations including any one of multiple traffic controls, resource expansions, and instance expansions; the disassembled matrix of the target node is calculated to obtain a target solution set of the target node, the target solution set including multiple solutions, the fitness of the multiple solutions in the target solution set satisfying a preset rule, and different solutions corresponding to different network configuration information of the target node; the cost overhead of each solution in the target solution set is calculated according to a preset cost overhead model; and the target node is configured according to the network configuration information corresponding to the target solution, the target solution being the solution corresponding to the minimum cost overhead in the target solution set. In this way, the embodiments of the present application can first calculate the disassembled matrix of the target node with congestion to obtain a target solution set including multiple solutions, different solutions corresponding to different network configuration information, then calculate the cost overhead of each solution in the target solution set according to a preset cost overhead model, and finally configure the target node according to the network configuration information corresponding to the solution with the minimum cost overhead, compared with the prior art of only increasing resource configuration, the target node can be configured with the network configuration information corresponding to the minimum cost overhead in multiple network configurations, thereby meeting the service quality requirements while reducing the configuration cost overhead of the Internet of Things.

[0038] In S101, the target node is a node with congestion in multiple nodes of the Internet of Things. In the Internet of Things, a node refers to a device or sensor in a network, which can be various physical devices, terminal devices, sensors, actuators, etc. Nodes play the role of data collection, transmission, and processing in the network. Each node has its own identifier and communication capability and can communicate and interact with other nodes through the network. The number of nodes in the Internet of Things is not fixed and can be flexibly configured according to actual needs. The number of nodes can be a few or tens of thousands, depending on the specific application scenario and scale.

[0039] The disassembled matrix can be used to represent the service quality influence information of the target node on multiple applications in the Internet of Things under different network configurations.

[0040] The network configuration can include any of a plurality of traffic controls, resource extensions, and instance extensions. The plurality of traffic controls can include four types of traffic control functions, namely, a classifier, a packet dropper, a delay device, and a scheduler. The resource extension is to add more resources to a node so that instances running on the node can obtain more resources. The instance extension is to add more virtual network function (VNF) and application network function (ANF) instances for carrying IoT applications to a node.

[0041] The classifier supports identifying the traffic of IoT applications according to predefined rules (including source and destination addresses, content types, use protocols, source and destination port numbers, etc., and the rules support customization in the form of a configuration file) and then adding an LSL label to different types of traffic. The label content is an integer, and the higher the number, the higher the priority of the traffic. Embodiments of the application predefine 1-10 as the label content (the label content supports extension in the configuration file).

[0042] The packet dropper supports discarding part or all of the messages according to the LSL label. The packet dropper needs to set a configuration file in advance to set the target messages to be discarded and the corresponding discard percentage. When the packet dropper receives a message, it first determines whether the message is a target message to be discarded. If so, it reads the discard percentage in the configuration file and compares it with the actual discard percentage of the target message. If the actual discard percentage is lower than the set value, the message is discarded. Otherwise, the message is forwarded.

[0043] The delay device supports delaying the forwarding of messages according to the LSL label. The delay device sets a configuration file in advance to set the time for which messages with different labels need to be delayed. When a message is received, the delay device parses the LSL label in the message and then matches it with the configuration file to obtain the corresponding delay time of the message. After waiting for the corresponding delay time, the message is forwarded.

[0044] The scheduler supports resetting the processing priority of messages according to the size of the value in the LSL label. The higher the LSL, the higher the priority, and the message is processed first. The lower the LSL, the lower the priority, and the message needs to wait until the high-priority messages are processed. When the LSL is the same, the first-come-first-processed principle is followed, and the messages are processed according to the time of arrival.

[0045] The deconstruction matrix of the target node can be used to obtain the quality of service influence information of the target node on the multiple applications in the Internet of Things under different network configurations, obtain the time delay influence coefficient of the target node on the multiple applications in the Internet of Things under different network configurations, and obtain the network configuration parameter of the target node on the multiple applications in the Internet of Things under different network configurations.

[0046] In S102, the target solution set can include multiple solutions, the fitness of the multiple solutions in the target solution set meets a preset rule, and different solutions correspond to different network configuration information of the target node. The fitness can be used to evaluate the fitness degree of each solution, and the higher the fitness is, the better it is. The fitness of the multiple solutions in the target solution set meets the preset rule, which can be that the fitness of the multiple solutions in the target solution set is greater than or equal to a preset fitness threshold, or the fitness of the target node under multiple network configurations is sorted from high to low, and the top 5 solutions are selected, and the number of solutions in the target solution set can be selected according to actual user requirements.

[0047] The deconstruction matrix of the target node can be used to obtain the quality of service influence information of the target node on the multiple applications in the Internet of Things under different network configurations, obtain the time delay influence coefficient of the target node on the multiple applications in the Internet of Things under different network configurations, and obtain the network configuration parameter of the target node on the multiple applications in the Internet of Things under different network configurations.

[0048] In S103, the preset cost overhead model can be Cost E2E The total sum of all expansion operation overheads on the node i, which is calculated as Wherein

[0049] In S104, the target solution is the solution corresponding to the minimum cost overhead in the target solution set.

[0050] The network configuration information corresponding to the target solution mentioned above refers to the network configuration information corresponding to the target solution. For example, it can be the combination configuration with the lowest cost among at least one combination configuration of multiple traffic control, resource expansion and instance expansion.

[0051] In some embodiments, the above-described S101 may specifically include:

[0052] Obtain information on the impact of target nodes on the quality of service of multiple applications in the Internet of Things under different network configurations;

[0053] Obtain the latency impact coefficient of the target node on multiple applications in the Internet of Things under different network configurations;

[0054] Obtain the network configuration parameters of the target node for multiple applications in the Internet of Things under different network configurations;

[0055] Based on multiple service quality impact information, latency impact coefficients, and network configuration parameters, construct the solution structure matrix of the target node.

[0056] The above-mentioned multiple service quality impact information can be represent The impact on all IoT applications varies, with different service quality levels affecting different applications.

[0057] The aforementioned time delay impact coefficient can be Represents decision variables A coefficient representing the impact of latency on IoT applications. For example, when... and but This can reduce latency in IoT applications by 25%, if This will increase latency by 25%.

[0058] The above network configuration parameters can be The information represented differs for each TCF or extended operation: For delayers: This represents the latency of IoT applications. For the scheduler: Represents the scheduling priority of IoT applications; for packet lossers, Represents the packet loss rate of IoT applications; the classifier has no direct impact on QoS. For vertical scaling and horizontal scaling: represents the overhead of scaling operations.

[0059] The solution structure matrix mentioned above includes multiple service quality impact information, latency impact coefficients, and network configuration parameters. For example, it can be represented by a binary vector X. θ This describes the flow control functionality or extended operations on the node. θ It can be used as an integer matrix T θrepresents, wherein the information includes a traffic control function TCF and an extended operation. wherein, represents the jth TCF or the extended operation on the node i, and the node i is an underloaded node. consists of a vector .

[0060] wherein, for the IoT application, z represents the total number of IoT applications, τ represents a certain IoT application, n represents the total number of nodes in the network, p represents the total number of traffic control functions, and m represents the total number of extended operations.

[0061] In the embodiment, by obtaining the multiple quality of service influence information of the target node on multiple applications in the Internet of Things under different network configurations, the time delay influence coefficient and the network configuration parameter, the solution structure matrix of the target node can be accurately constructed, and the target solution set of the target node can be accurately calculated.

[0062] In some embodiments, the above S102 can specifically include:

[0063] The solution structure matrix of the target node is initialized, a target population is generated, and the iteration number is set to one, the target population includes multiple individuals, and different individuals correspond to different network configuration information of the target node;

[0064] According to the preset model, the fitness of each individual in the target population is calculated;

[0065] The individuals in the target population whose fitness satisfies the preset rule are determined as target individuals, and the target individuals are multiple;

[0066] The multiple target individuals are subjected to cross mutation processing to obtain multiple mutated individuals, and the fitness of each mutated individual is calculated according to the preset model;

[0067] The target population is updated, the target population is multiple individuals whose fitness satisfies the preset rule in the multiple target individuals and the multiple mutated individuals, and the iteration number is increased by one;

[0068] In the case where the iteration number reaches the preset threshold, the multiple individuals in the target population whose fitness satisfies the preset rule are determined as the target solution set.

[0069] In some embodiments, if the number of iterations does not reach the preset threshold, the step of "determining individuals in the target population whose fitness meets the preset rule as target individuals, the target individuals being a plurality; performing cross and mutation processing on the plurality of target individuals to obtain a plurality of mutated individuals, and calculating the fitness of each mutated individual according to a preset model; updating the target population, the target population being a plurality of individuals in the plurality of target individuals and the plurality of mutated individuals whose fitness meets the preset rule, and adding one to the number of iterations" is returned to continue iteration until the number of iterations reaches the preset threshold, and finally a target solution set is obtained.

[0070] In the above, the plurality of target individuals are cross and mutation processed to obtain a plurality of mutated individuals. For example, offspring including the plurality of mutated individuals can be generated through cross and mutation. The cross strategy used is semi-uniform cross (HUX), which is based on a probability C p Half of the mismatched bits of the two solutions are exchanged. Then, a mutation operation is performed on the individual, and the mutation operation selects a bit flip strategy. The mutation operation is performed on each individual with a probability M p The value of the bit (0 and 1 are exchanged). Generally, M p = 1 / l, and l represents the length of the chromosome.

[0071] In this embodiment, by initializing the solution structure matrix of the target node to generate a target population, performing individual selection, cross and mutation, and iterative updating processing on the target population, a target solution set whose fitness meets the preset rule can be accurately obtained.

[0072] In some embodiments, the fitness of each individual in the target population can be calculated according to a preset model, which can specifically include:

[0073] According to the preset model, a plurality of service quality indicator values of each individual in the target population are calculated, the plurality of service quality indicator values being service quality indicator values corresponding to a plurality of applications in the Internet of Things;

[0074] The ratio of the plurality of service quality indicator values of each individual to a plurality of preset service quality threshold values is calculated, the plurality of service quality threshold values being service quality threshold values corresponding to the plurality of applications in the Internet of Things;

[0075] The plurality of ratios of each individual are minimized to calculate the fitness of each individual in the target population.

[0076] The service quality indicator value can exemplarily include at least one of latency, throughput, and unavailability. The latency refers to the time required for data to be transmitted and received, including transmission delay, processing delay, and queuing delay, etc. The throughput refers to the amount of data that a system or network can process per unit of time, which is usually measured in bits per second (bps) or the number of data packets. The unavailability refers to the proportion of time that a system or service is unavailable, which is usually expressed in percentage.

[0077] The above minimization of the plurality of ratios of each individual can exemplarily be wherein,

[0078] In the present embodiment, the optimization target is to minimize the ratio between the QoS requirements (preset quality of service threshold: latency QoS requirement throughput QoS requirement unavailability QoS requirement ) of the IoT application and the QoS (end-to-end delay end-to-end throughput and end-to-end unavailability ) provided by the Internet of Things platform node, so as to provide the highest QoS guarantee as possible.

[0079] In some embodiments, the above preset model can include a preset latency calculation sub-model, a preset throughput calculation sub-model and a preset unavailability calculation sub-model;

[0080] The above calculation of the plurality of quality of service index values of each individual in the target population according to the preset model can specifically include:

[0081] According to the preset latency calculation sub-model, a plurality of latencies of each individual in the target population are calculated, different latencies corresponding to different applications in the Internet of Things;

[0082] According to the preset throughput calculation sub-model, a plurality of throughputs of each individual in the target population are calculated, different throughputs corresponding to different applications in the Internet of Things;

[0083] According to the preset unavailability calculation sub-model, a plurality of unavailability of each individual in the target population are calculated, different unavailability corresponding to different applications in the Internet of Things;

[0084] The quality of service index value includes latency, throughput and unavailability.

[0085] The above preset latency calculation sub-model can exemplarily be an end-to-end latency calculation model, and the end-to-end latency is the sum of the local latencies of the IoT application τ on n nodes, i.e. It is assumed that when the benefit η i is greater than 100, the latency of the IoT application is 0. Otherwise, the latency on the node i is (1-η i % ) of the monitored latency, i.e. wherein, δ i is the monitored latency of the node i, η i represents the benefit of the node i, and is the sum of the benefits brought by all TCFs and expansion operations on the node i, which is calculated as follows: p is the total number of TCFs, m is the total number of expansion operations, and fq a is the benefit of TCF q, a c F is the benefit of extension operation c, F i A is the set of all TCFs supported by node i, A i is the set of all extension operations supported by node i.

[0086] The preset throughput calculation sub-model can exemplarily be an end-to-end throughput calculation model. The end-to-end throughput of the IoT application τ is the minimum value among throughputs of all nodes. The calculation manner is wherein, represents the throughput of the IoT application τ on the node i. The calculation manner is: ξ i is the sum of the benefit increase of all extension operations supported by the node i on the throughput. The calculation manner is When there is no scheduler deployed on the node i or the node does not support the deployment of the scheduler, the throughput of the node i is the sum of the monitored throughput and ξ i . Otherwise, the throughput needs to be increased by a weight The calculation manner is f scheduler is the benefit of the scheduler.

[0087] The preset unavailability calculation sub-model can exemplarily be an end-to-end unavailability calculation model. The end-to-end unavailability is the sum of unavailability of the IoT application τ on all nodes. The calculation manner is: It is assumed that if there is no packet dropper on the node i or the node does not support the deployment of the packet dropper, the unavailability of the node is 0. If there is a packet dropper on the first node, the unavailability of the first node is the rejection percentage corresponding to the IoT application τ. Otherwise, the unavailability is the availability influence factor multiplied by the rejection percentage associated with the IoT application τ. The calculation manner is as follows:

[0088] wherein, f dropper is the benefit of the packet dropper, ε i is the availability influence factor of the packet dropper on the node i. The calculation manner is

[0089] In this embodiment, according to the preset delay calculation sub-model, the preset throughput calculation sub-model and the preset unavailability calculation sub-model, the multiple delays, the multiple throughputs and the multiple unavailability of each individual in the target population can be accurately calculated.

[0090] As an implementation manner of the present application, in order to realize the configuration of the target node with the minimum cost overhead and the minimum resource usage, before the S104, the method can further include:

[0091] In the case that there are multiple solutions corresponding to the minimum cost overhead in the target solution set, the multiple solutions corresponding to the minimum cost overhead in the target solution set are determined as the candidate solution set;

[0092] According to the preset resource usage model, the resource usage of each solution in the candidate solution set is calculated;

[0093] The solution corresponding to the minimum resource usage in the candidate solution set is determined as the target solution.

[0094] The preset resource usage model may be, for example, the resource usage of the end-to-end TCF deployment, denoted as RU E2E , which is equal to the sum of the resource usage associated with the deployment of the TCF on all nodes, and is calculated as wherein, β i is the CPU usage involved in the execution of the expansion operation and the deployment of the TCF in node i, and is calculated as γ i is the RAM usage involved in the execution of the expansion operation and the deployment of the TCF in node i, and is calculated as wherein, cpu q is the CPU usage of the TCF q, ram q is the RAM usage of the TCF q, is the CPU usage of node i, is the RAM usage of node i. The CPU and RAM usage of the TCF depends on the request arrival rate λ on node i.

[0095] In the case that there are multiple solutions corresponding to the minimum cost overhead in the target solution set, the multiple solutions corresponding to the minimum cost overhead in the target solution set are determined as the candidate solution set, and according to the preset resource usage model, the resource usage of each solution in the candidate solution set is calculated, and finally the solution corresponding to the minimum resource usage in the candidate solution set is determined as the target solution. The target solution obtained in this way is the solution with the minimum cost overhead and the minimum resource usage, thereby realizing the configuration of the target node with the minimum cost overhead and the minimum resource usage.

[0096] In order to facilitate the understanding of the method for configuring the Internet of Things node in the embodiments of the present application, the actual application process of the method for configuring the Internet of Things node is described.

[0097] The IoT end-to-end QoS guarantee method with cost saving provided by the embodiment of the application is directed to an IoT platform supporting an NFV architecture, provides traffic control functions based on VNF and ANF, supports deployment of the traffic control functions on nodes and horizontal and vertical expansion of the nodes, models problems of QoS indicators, resource usage, cost and other optimization targets, and uses a genetic algorithm to solve the problems, so that the resource usage and cost overhead are effectively controlled under the premise of guaranteeing the end-to-end QoS guarantee. Figure 2 As shown in the figure, the IoT end-to-end QoS guarantee method with cost saving provided by the embodiment of the application has the following specific steps:

[0098] S1. Constructing traffic control functions based on VNF / ANF. The embodiment of the application supports four types of traffic control functions, namely, a classifier, a packet dropper, a delay device, and a scheduler.

[0099] Classifier. The classifier supports identifying the traffic of an IoT application according to predefined rules (including source and destination addresses, content types, use protocols, source and destination port numbers, and the rules support customization and are written in the form of a configuration file), and then adding an LSL label to different types of traffic, with the label content being an integer, and the higher the number, the higher the priority of the traffic. The embodiment of the application predefines 1-10 as the label content (the label content supports extension in the configuration file).

[0100] Packet dropper. The packet dropper supports discarding part or all of the messages according to the LSL label. The packet dropper needs to be pre-set with a configuration file for setting target messages to be discarded and a corresponding discarding percentage. When the packet dropper receives a message, it first determines whether the message is a target message to be discarded. If so, the discarding percentage in the configuration file is read, and the actual discarding percentage of the target message is compared. If the actual discarding percentage is lower than the set value, the message is discarded, otherwise the message is forwarded.

[0101] Delay device. The delay device supports delaying the forwarding of messages according to the LSL label. The delay device pre-sets a configuration file to set the time for which messages with different labels need to be delayed. When a message is received, the delay device parses the LSL label in the message, and then matches the LSL label with the configuration file to obtain the corresponding delay time of the message, and forwards the message after waiting for the corresponding delay time.

[0102] Scheduler. The scheduler supports resetting the processing priority of a message according to the size of the value in the LSL label. The higher the LSL, the higher the priority, and the message is processed first. When the LSL is the same, the principle of first come first served is followed, and the messages are processed according to the time of arrival.

[0103] S2. Define node expansion operations. In this embodiment, to ensure end-to-end QoS of the IoT application, in addition to deploying traffic control functions, node expansion operations are also required to ensure that the IoT application has sufficient resources. Expansion operations are divided into vertical expansion and horizontal expansion. Vertical expansion (i.e., the resource expansion mentioned above) involves adding more resources to a node so that instances hosting this node can obtain more resources. Horizontal expansion (i.e., the instance expansion mentioned above) involves adding more VNF and ANF instances to a node to host the IoT application.

[0104] The embodiments of this application mainly address the QoS guarantee problem, and will not provide much explanation of the specific deployment process of the traffic control function and the specific execution process of the extended operation.

[0105] S3. Construct an end-to-end model of QoS metrics, costs, and resource overhead.

[0106] For IoT applications, let z represent the total number of IoT applications, τ represent a specific IoT application, and n represent the total number of nodes in the network. Calculate QoS metrics for a given application τ, including: end-to-end latency L. E2E End-to-end throughput T E2E End-to-end unavailability U E2E Furthermore, the resource usage RU involved in TCF deployment and node expansion operations is calculated. E2E And the cost involved in performing extended operations. E2E .

[0107] S3.1. Construct a QoS indicator model.

[0108] End-to-end latency calculation model: End-to-end latency is the sum of the local latency τ of the IoT application on n nodes, i.e. Assume that when the return η i When the value is greater than 100, the latency of the IoT application is 0. Otherwise, the latency at node i is (1-η) times the monitored latency. i %),Right now Where, δ i Let η be the monitoring delay for node i. i The revenue representing node i is the sum of the revenues from all TCFs and the expansion operations on node i, and it is calculated as follows: p is the total number of TCFs, m is the total number of expansion operations, and f q For the return of TCF q, a c To extend the benefits of operation c, F i Let A be the set of all TCFs supported by node i. i This is the set of all extended operations supported by node i.

[0109] End-to-end throughput computation model: The end-to-end throughput of IoT application τ is the minimum of its throughput across all nodes, computed as where, represents the throughput of IoT application τ on node i, computed as: ξ i is the sum of the throughput gain of all extension operations supported by node i, computed as When there is no scheduler deployed on node i or the node does not support the deployment of a scheduler, the throughput of node i is the sum of the monitored throughput and ξ i . Otherwise, the throughput needs to be increased by a weight , computed as f scheduler is the gain of the scheduler.

[0110] End-to-end unavailability computation model: The end-to-end unavailability of IoT application τ is the sum of its unavailability across all nodes, computed as: Assume that if there is no packet dropper on node i or the node does not support the deployment of a packet dropper, the unavailability of this node is 0. If there is a packet dropper on the first node, the unavailability of the first node is the rejection percentage of IoT application τ. Otherwise, the unavailability is the availability impact factor multiplied by the rejection percentage associated with IoT application τ. The computation is as follows:

[0111] where, f dropper is the gain of the packet dropper, ε i is the impact factor of the packet dropper on the unavailability of node i, computed as

[0112] S3.2. Constructing the extension operation cost overhead model.

[0113] Let Cost E2E represent the sum of the overhead of all extension operations on node i, computed as where

[0114] S3.3. Constructing the resource usage model.

[0115] The resource usage of end-to-end TCF deployment is denoted by RU E2E , which is equal to the sum of the resource usage associated with the deployment of TCF on all nodes, computed as where, β iThe CPU usage amount involved in performing the extension operation and deploying the TCF in the node i is calculated as γ i The RAM usage amount involved in performing the extension operation and deploying the TCF in the node i is calculated as wherein cpu q is the CPU usage amount of the TCF q, and ram q is the RAM usage amount of the TCF q, is the CPU usage amount of the node i, is the RAM usage amount of the node i. The CPU and RAM usage amounts of the TCF depend on the request arrival rate λ on the node i.

[0116] S4. Determine the objective function to be solved

[0117] According to the model constructed in S3, the optimization objective, i.e. the objective function, is set, which is to minimize the ratio between the QoS requirements (preset values: latency QoS requirement throughput QoS requirement unavailability QoS requirement ) of the IoT application and the QoS (end-to-end delay end-to-end throughput and end-to-end unavailability ) provided by the nodes of the Internet of Things platform, i.e. to provide the highest QoS guarantee as possible.

[0118] The optimization objective (objective function) can be expressed as: wherein,

[0119] S5. Construct the solution space structure (chromosome structure)

[0120] Based on the above steps, the structure of the solution is defined as follows. The genetic algorithm is introduced to solve the optimization objective, in which a chromosome is a solution, and the structure of the solution is defined as the structure of the chromosome.

[0121] The chromosome is defined as a binary vector X θ to describe the situation of the flow control function or the extension operation on the node. X θ corresponds to an integer matrix T θ which contains the information of the flow control function TCF and the extension operation. wherein, represents the jth TCF or extension operation on the node i, and the node i is the underloaded node, i.e. the above-mentioned target node. is composed of the vector , i.e. the above-mentioned solution structure matrix.

[0122] The chromosome structure is as followsFigure 3 p represents the total number of traffic control functions, m represents the total number of scaling operations, and z represents the total number of all IoT applications.

[0123] represents the impact on all IoT applications.

[0124] represents the decision variable the impact on the latency of the IoT application, for example, when and then the latency of the IoT application can be reduced by 25%, if then the latency is increased by 25%.

[0125] For each TCF or scaling operation, the information represented is different: for the delayer: the delay time of the IoT application. For the scheduler: the scheduling priority of the IoT application; for the packet dropper, the packet drop rate of the IoT application; the classifier has no direct impact on QoS. For vertical scaling, horizontal scaling: the overhead of the scaling operation.

[0126] S6. Obtain the Pareto solution of the solving target based on the NSGAII genetic algorithm.

[0127] S6.1. First, randomly initialize the population. According to the chromosome structure in S5, generate the initial population (equivalent to the above target population). Set the iteration number t = 1.

[0128] S6.2. Calculate the fitness of each individual according to the model in S3.1.

[0129] S6.3. Individual selection. Apply the tournament selector in the population, determine the optimal individual in the initial population according to the fitness and optimization target, and put it into the mating pool.

[0130] S6.4. Cross and mutate. Cross the individuals in the mating pool, and the cross strategy adopted is half-uniform crossover (HUX), which exchanges half of the mismatched bits of the two solutions according to the probability C p . Then mutate the individual, and the mutation operation selects the bit flip strategy, which changes the value of the bit (0 and 1 are exchanged) in each individual with a probability M p . Generally, M p = 1 / l, l represents the length of the chromosome. Offspring is generated through cross and mutation.

[0131] S6.5. Based on the elite retention strategy, select the optimal individual from the combination of parent and offspring to obtain a new generation of offspring population, and increment the iteration count t by 1. When the iteration count reaches a pre-set threshold, the algorithm ends, and the individual in the latest offspring population is the current optimal individual, which is the optimal solution set for solving the objective function (i.e., the objective solution set mentioned above).

[0132] S7. Selecting the optimal solution based on a cost-optimal strategy. Based on the optimal solution set obtained in S6, this application embodiment provides a method for selecting a unique solution based on a cost-optimal strategy.

[0133] Based on the extended operation cost model of S3.3, the extended operation cost is calculated for each solution in the optimal solution set, and multiple solutions with the lowest cost are selected to form a temporary solution set.

[0134] Then, based on the resource usage model in S3.2, the resource usage is calculated for each solution in the temporary solution set, and the solution with the least resource usage is selected as the final unique optimal solution (i.e., the target solution mentioned above) and output.

[0135] In this embodiment, by dynamically deploying network traffic control functions on underloaded nodes, the purpose of fully utilizing the allocated idle resources in the nodes is achieved without increasing additional resource configuration costs. This reduces the waste of idle resources, realizes rational resource utilization, and effectively controls costs. Considering multiple indicators affecting the QoS of IoT applications, such as latency, throughput, and unavailability, a multi-objective optimization problem and solution structure are constructed. A genetic algorithm is used to generate the optimal solution set through multiple iterations. A cost-based optimal solution selection method is used to select the unique optimal solution, achieving minimum cost and resource overhead while ensuring end-to-end QoS requirements.

[0136] Based on the IoT node configuration method provided in the above embodiments, this application also provides specific implementation methods of IoT node configuration devices, please refer to the following embodiments.

[0137] like Figure 4 As shown, the IoT node configuration device 400 provided in this application embodiment may include the following modules: a construction module 401, a first computing module 402, a second computing module 403, and a configuration module 404.

[0138] Module 401 is used to construct the solution structure matrix of the target node. The solution structure matrix is ​​used to characterize the service quality impact information of the target node on multiple applications in the Internet of Things under different network configurations. The network configuration includes any one of various flow control, resource expansion and instance expansion.

[0139] The first calculation module 402 is configured to calculate the disassembled matrix of the target node to obtain a target solution set of the target node, the target solution set including multiple solutions, the fitness of the multiple solutions in the target solution set satisfying a preset rule, and different solutions corresponding to different network configuration information of the target node.

[0140] The second calculation module 403 is configured to calculate the cost overhead of each solution in the target solution set according to a preset cost overhead model.

[0141] The configuration module 403 is configured to configure the target node according to the network configuration information corresponding to the target solution, the target solution being the solution corresponding to the minimum cost overhead in the target solution set.

[0142] The Internet of Things node configuration device provided in the embodiments of the present application can construct a disassembled matrix of a target node, the disassembled matrix being used to represent the service quality influence information of the target node under different network configurations on multiple applications in the Internet of Things, the network configurations including any one of multiple traffic control, resource expansion and instance expansion; the disassembled matrix of the target node is calculated to obtain a target solution set of the target node, the target solution set including multiple solutions, the fitness of the multiple solutions in the target solution set satisfying a preset rule, and different solutions corresponding to different network configuration information of the target node; the cost overhead of each solution in the target solution set is calculated according to a preset cost overhead model; and the target node is configured according to the network configuration information corresponding to the target solution, the target solution being the solution corresponding to the minimum cost overhead in the target solution set. In this way, the embodiments of the present application can first calculate the disassembled matrix of the target node under congestion to obtain a target solution set including multiple solutions, different solutions corresponding to different network configuration information, then calculate the cost overhead of each solution in the target solution set according to a preset cost overhead model, and finally configure the target node according to the network configuration information corresponding to the solution with the minimum cost overhead, so that compared with the prior art which only increases resource configuration, the target node can be configured with the network configuration information corresponding to the minimum cost overhead in multiple network configurations, thereby meeting the service quality requirement while reducing the configuration cost overhead of the Internet of Things.

[0143] In some embodiments, the above-mentioned construction module 401 can specifically include:

[0144] The first obtaining sub-module is configured to obtain multiple service quality influence information of the target node under different network configurations on multiple applications in the Internet of Things;

[0145] The second obtaining sub-module is configured to obtain a delay influence coefficient of the target node under different network configurations on multiple applications in the Internet of Things;

[0146] The third obtaining sub-module is configured to obtain a network configuration parameter of the target node under different network configurations on multiple applications in the Internet of Things.

[0147] The constructing submodule is configured to construct a disassembled matrix of the target node according to the multiple quality of service influence information, the time delay influence coefficient, and the network configuration parameter.

[0148] In some embodiments, the first calculating module 402 can specifically include:

[0149] The initializing submodule is configured to initialize the disassembled matrix of the target node, generate a target population, and set an iteration number to one, the target population including multiple individuals, and different individuals corresponding to different network configuration information of the target node.

[0150] The calculating submodule is configured to calculate the fitness of each individual in the target population according to a preset model.

[0151] The first determining submodule is configured to determine individuals in the target population whose fitness satisfies a preset rule as target individuals, the target individuals being multiple.

[0152] The crossover and mutation submodule is configured to perform crossover and mutation processing on the multiple target individuals to obtain multiple mutated individuals, and calculate the fitness of each mutated individual according to the preset model.

[0153] The updating submodule is configured to update the target population, the target population being multiple individuals in the multiple target individuals and the multiple mutated individuals whose fitness satisfies the preset rule, and increase the iteration number by one.

[0154] The second determining submodule is configured to determine multiple individuals in the target population whose fitness satisfies the preset rule as a target solution set when the iteration number reaches a preset threshold.

[0155] In some embodiments, the calculating submodule can specifically include:

[0156] The first calculating unit is configured to calculate multiple quality of service index values of each individual in the target population according to a preset model, the multiple quality of service index values being quality of service index values corresponding to multiple applications in the Internet of Things.

[0157] The second calculating unit is configured to calculate ratios of the multiple quality of service index values of each individual to preset multiple quality of service thresholds, the multiple quality of service thresholds being quality of service thresholds corresponding to the multiple applications in the Internet of Things.

[0158] The third calculating unit is configured to minimize the multiple ratios of each individual to calculate the fitness of each individual in the target population.

[0159] In some embodiments, the preset model can include a preset time delay calculating submodel, a preset throughput calculating submodel, and a preset unavailability calculating submodel.

[0160] The first calculating unit can specifically include:

[0161] The first calculation subunit is configured to calculate a plurality of time delays of each individual in the target population according to a preset time delay calculation submodel, wherein different time delays correspond to different applications in the Internet of Things;

[0162] The second calculation subunit is configured to calculate a plurality of throughputs of each individual in the target population according to a preset throughput calculation submodel, wherein different throughputs correspond to different applications in the Internet of Things;

[0163] The third calculation subunit is configured to calculate a plurality of unavailability of each individual in the target population according to a preset unavailability calculation submodel, wherein different unavailability correspond to different applications in the Internet of Things.

[0164] The quality of service index value includes the time delay, the throughput and the unavailability.

[0165] As an implementation manner of the present application, in order to achieve the configuration of the target node with the minimum cost overhead and the minimum resource usage, the apparatus 400 can further include:

[0166] The first determination module is configured to, in the case that the solution corresponding to the minimum cost overhead in the target solution set has a plurality of solutions, determine the plurality of solutions corresponding to the minimum cost overhead in the target solution set as a candidate solution set.

[0167] The third calculation module is configured to calculate the resource usage of each solution in the candidate solution set according to a preset resource usage model.

[0168] The second determination module is configured to determine the solution corresponding to the minimum resource usage in the candidate solution set as the target solution.

[0169] Figure 5 A hardware structure schematic diagram of an electronic device provided by an embodiment of the present application is shown.

[0170] The electronic device can include a processor 501 and a memory 502 having computer program instructions stored therein.

[0171] Specifically, the processor 501 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or can be configured as one or more integrated circuits implementing the embodiments of the present application.

[0172] The memory 502 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 502 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or a digital versatile disc (DVD)), a solid-state drive (SSD), a USB drive, or a combination of two or more of these. Where appropriate, the memory 502 can include removable or non-removable (or fixed) media. Where appropriate, the memory 502 can be internal or external to the integrated gateway disaster recovery device. In particular embodiments, the memory 502 is non-volatile, solid-state memory.

[0173] In particular embodiments, the memory 502 can include read-only memory (ROM), random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to

[0174] The processor 501 implements the configuration method of the Internet of Things node in any of the above embodiments by reading and executing the computer program instructions stored in the memory 502.

[0175] In one example, the electronic device can further include a communication interface 503 and a bus 510. As shown, the processor 501, the memory 502, and the communication interface 503 are connected through the bus 510 and complete communication with each other. Figure 5

[0176] The communication interface 503 is mainly used to realize the communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0177] ​Bus 510 includes hardware, software, or both, to couple electronic devices to each other in a network. While Figure 5 illustrates a bus, other interconnects that are used to interconnect various hardware components can be utilized. Although Figure 5 is described and shown as including a particular number and configuration of components, this application contemplates that any suitable number and configuration of components can be utilized.

[0178] The electronic device can perform the method for configuring an Internet of Things node in the embodiments of the application, thereby realizing the method for configuring an Internet of Things node and the apparatus described in combination Figure 1 and Figure 4 with the above embodiments.

[0179] In addition, in combination with the method for configuring an Internet of Things node in the above embodiments, the embodiments of the application can provide a computer-readable storage medium to realize. The computer-readable storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to realize any one of the above embodiments of the method for configuring an Internet of Things node.

[0180] In combination with the method for configuring an Internet of Things node in the above embodiments, the embodiments of the application can provide a computer program product, instructions in the computer program product are executed by a processor of an electronic device to make the electronic device execute the method for configuring an Internet of Things node in any one of the above.

[0181] It needs to be clear that the application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after understanding the spirit of the application.

[0182] The functions noted in the description of the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, functional cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0183] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps mentioned above, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0184] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0185] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A method for configuring Internet of Things (IoT) nodes, characterized in that, include: Construct a solution structure matrix for the target node. The solution structure matrix is ​​used to characterize the service quality impact information of the target node on multiple applications in the Internet of Things under different network configurations. The network configurations include any one of various traffic control, resource expansion, and instance expansion. The solution structure matrix of the target node is calculated to obtain the target solution set of the target node. The target solution set includes multiple solutions. The fitness of multiple solutions in the target solution set satisfies a preset rule. Different solutions correspond to different network configuration information of the target node. Calculate the cost of each solution in the target solution set according to the preset cost model; The target node is configured according to the network configuration information corresponding to the target solution, and the target solution is the solution with the minimum cost in the target solution set.

2. The method according to claim 1, characterized in that, The solution structure matrix for constructing the target node includes: Obtain information on the impact of the target node on the quality of service of multiple applications in the Internet of Things under different network configurations; Obtain the latency impact coefficient of the target node on multiple applications in the Internet of Things under different network configurations; Obtain the network configuration parameters of the target node for multiple applications in the Internet of Things under different network configurations; Based on the multiple service quality impact information, the latency impact coefficient, and the network configuration parameters, construct the solution structure matrix of the target node.

3. The method according to claim 1, characterized in that, The calculation of the solution structure matrix of the target node to obtain the target solution set of the target node includes: The solution structure matrix of the target node is initialized to generate a target population, and the number of iterations is set to one. The target population includes multiple individuals, and different individuals correspond to different network configuration information of the target node. According to the preset model, calculate the fitness of each individual in the target population; Individuals in the target population whose fitness satisfies a preset rule are identified as target individuals, and there are multiple target individuals. Multiple target individuals are subjected to crossover mutation to obtain multiple mutated individuals, and the fitness of each mutated individual is calculated according to the preset model. The target population is updated, which consists of multiple target individuals and multiple mutated individuals whose fitness satisfies the preset rule, and the iteration number is incremented by one. When the number of iterations reaches a preset threshold, multiple individuals in the target population whose fitness satisfies the preset rule are identified as the target solution set.

4. The method according to claim 3, characterized in that, The step of calculating the fitness of each individual in the target population according to a preset model includes: According to a preset model, multiple service quality index values ​​are calculated for each individual in the target population, and the multiple service quality index values ​​are the service quality index values ​​corresponding to multiple applications in the Internet of Things. Calculate the ratio of multiple service quality index values ​​of each individual to multiple preset service quality thresholds, wherein the multiple service quality thresholds are the service quality thresholds corresponding to multiple applications in the Internet of Things; The fitness of each individual in the target population is calculated by minimizing multiple ratios of each individual.

5. The method according to claim 4, characterized in that, The preset model includes a preset latency calculation sub-model, a preset throughput calculation sub-model, and a preset unavailability calculation sub-model; Based on a preset model, multiple service quality index values ​​are calculated for each individual in the target population, including: According to the preset latency calculation sub-model, multiple latencys of each individual in the target population are calculated, and different latencys correspond to different applications in the Internet of Things; According to the preset throughput calculation sub-model, the throughput of each individual in the target population is calculated, and different throughputs correspond to different applications in the Internet of Things; According to the preset unavailability calculation sub-model, multiple unavailabilityes of each individual in the target population are calculated, and different unavailabilityes correspond to different applications in the Internet of Things; The service quality metrics include the latency, the throughput, and the unavailability.

6. The method according to claim 1, characterized in that, Before configuring the target node according to the network configuration information corresponding to the target solution, the method further includes: If there are multiple solutions corresponding to the minimum cost in the target solution set, the multiple solutions corresponding to the minimum cost in the target solution set are determined as a candidate solution set; Based on the preset resource usage model, calculate the resource usage of each solution in the candidate solution set; The solution with the minimum resource usage in the candidate solution set is determined as the target solution.

7. An Internet of Things (IoT) node configuration device, characterized in that, The device includes: A construction module is used to construct a solution structure matrix of the target node. The solution structure matrix is ​​used to characterize the service quality impact information of the target node on multiple applications in the Internet of Things under different network configurations. The network configuration includes any one of various traffic control, resource expansion and instance expansion. The first calculation module is used to calculate the solution structure matrix of the target node to obtain the target solution set of the target node. The target solution set includes multiple solutions, and the fitness of multiple solutions in the target solution set satisfies a preset rule. Different solutions correspond to different network configuration information of the target node. The second calculation module is used to calculate the cost of each solution in the target solution set according to a preset cost model. The configuration module is used to configure the target node according to the network configuration information corresponding to the target solution, wherein the target solution is the solution with the minimum cost in the target solution set.

8. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the IoT node configuration method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the IoT node configuration method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the IoT node configuration method as described in any one of claims 1-6.

Images