Computing Resource Dynamic Allocation Method and System Based on Industrial Internet of Things Data Center

Abstract

The present application provides a method and system for dynamically allocating computing resources based on an industrial Internet of Things data center. The method includes: receiving business needs of enterprise users through an industrial Internet of Things user platform, and issuing the business needs to the data computing center of the industrial Internet of Things management platform through an industrial Internet of Things service platform; monitoring the resource data of the business management sub-platform through a monitoring module; determining the resource demand characteristics of the enterprise users based on the business needs; determining resource allocation parameters based on the resource demand characteristics and the resource data of the business management sub-platform; and generating resource allocation instructions according to the resource allocation parameters through a control center. This method can dynamically allocate computing resources to different sub-platforms to optimize the execution of computing tasks and ensure stable operation and efficient scheduling of the production line.

Description

Technical Field

[0001] This specification relates to the field of data processing, and in particular to a method and system for dynamically allocating computing resources based on an industrial Internet of Things data center. Background Art

[0002] With the advent of Industry 4.0, the Industrial Internet of Things (IIoT) has become a core driver of the intelligent transformation of manufacturing. In IIoT-enabled production lines, numerous sensors, intelligent devices, and control systems are interconnected, creating a highly integrated, data-driven production environment. Within this environment, efficient production line operation relies on the real-time processing and analysis of massive amounts of data, as well as the precise allocation of computing resources. However, given the vastly varying needs of diverse businesses, dynamically allocating computing resources to IIoT platforms within the limited computing resources of data centers has become a major challenge facing industrial production.

[0003] Based on this, this specification provides a system and method for dynamically allocating computing resources based on an industrial Internet of Things data center, which dynamically allocates computing resources to different sub-platforms to optimize the execution of computing tasks and ensure stable operation and efficient scheduling of production lines. Summary of the Invention

[0004] One or more embodiments of the present specification provide a dynamic computing resource allocation system based on an Industrial Internet of Things (IIoT) data center. The system includes an IIoT user platform, an IIoT service platform, an IIoT management platform, an IIoT sensor network platform, and an IIoT perception control platform. The IIoT user platform is configured to receive business requirements of enterprise users and transmit the business requirements to the data computing center of the IIoT management platform through the IIoT service platform. The IIoT management platform includes the data computing center, a business management sub-platform, and a control center. The business management sub-platform includes a monitoring module configured to monitor resource data of the business management sub-platform. The control center is configured to: determine resource requirement characteristics of the enterprise users based on the business requirements; determine resource allocation parameters based on the resource requirement characteristics and the resource data of the business management sub-platform; the resource allocation parameters include computing resources corresponding to computing tasks; the control center is further configured to generate resource allocation instructions based on the resource allocation parameters; the resource allocation instructions are configured to: establish a process corresponding to the computing task; and bind the process corresponding to the computing task to a resource core corresponding to the computing task, where the resource core is determined based on the resource allocation parameters.

[0005] One or more embodiments of this specification provide a method for dynamically allocating computing resources based on an industrial Internet of Things data center. The method is executed by a control center of an industrial Internet of Things management platform based on a dynamic allocation system for computing resources of an industrial Internet of Things data center. The system includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, the industrial Internet of Things management platform, an industrial Internet of Things sensor network platform, and an industrial Internet of Things perception control platform; the industrial Internet of Things management platform includes a data computing center, a business management sub-platform, and the control center; the business management sub-platform includes a monitoring module; the method includes: receiving business needs of enterprise users through the industrial Internet of Things user platform, and transmitting the business needs through the industrial Internet of Things The service platform sends data to the data computing center of the industrial Internet of Things management platform; monitors the resource data of the business management sub-platform through the monitoring module; determines the resource demand characteristics of the enterprise user based on the business needs; determines the resource allocation parameters based on the resource demand characteristics and the resource data of the business management sub-platform; the resource allocation parameters include the computing resources corresponding to the computing task; generates resource allocation instructions according to the resource allocation parameters through the control center; the resource allocation instructions are configured to: establish a process corresponding to the computing task; bind the process corresponding to the computing task to the resource core corresponding to the computing task, and the resource core is determined based on the resource allocation parameters.

[0006] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for dynamically allocating computing resources based on an industrial Internet of Things data center.

[0007] Beneficial effect: The method and system for dynamic allocation of computing resources based on an industrial Internet of Things data center based on this application can realize dynamic allocation of computing resources based on the industrial Internet of Things, which can effectively improve the efficiency of business processing and further improve resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 This is a schematic diagram of the platform structure of a dynamic allocation system for computing resources based on an industrial Internet of Things data center according to some embodiments of this specification;

[0010] Figure 2is an exemplary flow chart of a method for dynamically allocating computing resources based on an industrial Internet of Things data center according to some embodiments of this specification;

[0011] Figure 3 is an exemplary schematic diagram of a demand estimation model according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart of determining resource allocation parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0015] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0016] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Because enterprise users have different business types and volumes, and different businesses (such as data statistics, data screening, data analysis, and data storage) involve different types of data and processing requirements, they also occupy different proportions of Industrial Internet of Things system resources. Therefore, there is a need for dynamic allocation of computing resources. Some embodiments of this specification provide a system and method for dynamic allocation of computing resources based on an Industrial Internet of Things data center, which can dynamically allocate resources to process the diverse business needs of enterprise users through the Industrial Internet of Things.

[0018] Figure 1 This is a schematic diagram of the platform structure of a dynamic allocation system of computing resources based on an industrial Internet of Things data center according to some embodiments of this specification.

[0019] In some embodiments, as Figure 1 As shown, the computing resource dynamic allocation system 100 based on the industrial Internet of Things data center may include an industrial Internet of Things user platform 110, an industrial Internet of Things service platform 120, an industrial Internet of Things management platform 130, an industrial Internet of Things sensor network platform 140 and an industrial Internet of Things perception control platform 150.

[0020] The IIoT user platform 110 is a platform for interacting with enterprise users. In some embodiments, the IIoT user platform 110 is configured to receive business needs of enterprise users and send the business needs to the IIoT service platform 120.

[0021] In some embodiments, the IIoT user platform 110 may be a platform based on a desktop computer, a tablet computer, a laptop computer, a mobile phone, or other electronic devices capable of data processing and data communication.

[0022] The Industrial Internet of Things service platform 120 is a platform for processing received business requests. In some embodiments, the Industrial Internet of Things service platform 120 can be implemented on a terminal or server. In some embodiments, the Industrial Internet of Things service platform 120 is configured to process business requests and then transmit them to the data computing center of the Industrial Internet of Things management platform 130.

[0023] In some embodiments, the IIoT service platform 120 can interact bidirectionally with the IIoT management platform 130. For example, after the IIoT management platform 130 calculates resource allocation parameters based on business needs and resource demand characteristics, it can upload the resource allocation results to the IIoT service platform 120, which can then upload them to enterprise users.

[0024] The IIoT management platform 130 is a platform for managing and controlling the IIoT data center-based computing resource dynamic allocation system 100. In some embodiments, the IIoT management platform 130 can be implemented based on a processor or server.

[0025] In some embodiments, the industrial Internet of Things management platform 130 may include a data computing center, a business management sub-platform, and a control center (not shown in the figure).

[0026] The data computing center can be used to manage resources and process data and / or information from at least one of its own components or external data sources (e.g., a cloud data center). In some embodiments, the data computing center can be configured with a single server or a server group, which can be centralized or distributed.

[0027] The business management sub-platform refers to the hardware device used to perform computing tasks in the dynamic computing resource allocation system 100 based on the Industrial Internet of Things data center. In some embodiments, the business management sub-platform may include a monitoring module configured to monitor resource data within the business management sub-platform. For example, the monitoring module may include server monitoring hardware, resource management software (such as Nagios or Zabbix), performance counters, and the like.

[0028] The control center is a component used to control the target computing terminals to perform data calculations and processing. In some embodiments, the control center may include computer equipment that the server relies on. In some embodiments, the control center is configured to determine the resource demand characteristics of enterprise users based on business needs; determine resource allocation parameters based on the resource demand characteristics and resource data from the business management sub-platform; the resource allocation parameters include the computing resources corresponding to the computing tasks.

[0029] In some embodiments, the control center is further configured to determine the resource demand characteristics of the enterprise user based on the production status data and business needs of the enterprise user.

[0030] In some embodiments, the control center is further configured to determine the resource demand characteristics of the enterprise user based on the production status data and business needs of the enterprise user and based on the demand prediction model, where the demand prediction model is a machine learning model.

[0031] In some embodiments, the control center is further configured to: determine candidate parameters; determine computing characteristics corresponding to the candidate parameters based on the candidate parameters, resource demand characteristics, and resource data; and determine resource allocation parameters based on the computing characteristics.

[0032] In some embodiments, the control center is further configured to: determine the computing features based on candidate parameters, resource demand characteristics, and resource data through a feature estimation model, where the feature estimation model is a machine learning model; determine the parameter evaluation value of the computing feature by taking into account the weighted value of the computing response speed, data congestion probability, and failure probability of the computing feature; and determine the resource allocation parameters based on the parameter evaluation value of the computing feature.

[0033] In some embodiments, the control center is further configured to generate resource allocation instructions based on resource allocation parameters; the resource allocation instructions are configured to: establish a process corresponding to the computing task; bind the process corresponding to the computing task to the resource core corresponding to the computing task, and the resource core is determined based on the resource allocation parameters.

[0034] In some embodiments, the IIoT management platform 130 may interact with the IIoT sensor network platform 140. For example, the IIoT management platform 130 may send a data collection instruction to the IIoT sensor network platform 140.

[0035] The IIoT sensor network platform 140 is a network used for data transmission in the IIoT data center-based computing resource dynamic allocation system 100. In some embodiments, the IIoT sensor network platform 140 may be configured with communication devices or servers.

[0036] In some embodiments, the IIoT sensor network platform 140 can interact with the IIoT perception control platform 150. For example, the IIoT sensor network platform 140 can receive relevant data on the production line collected by the IIoT perception control platform 150 and transmit the data to the IIoT management platform 130, which further processes and analyzes the data.

[0037] The industrial Internet of Things perception control platform 150 is a platform for monitoring and controlling the production process.

[0038] In some embodiments, the IIoT perception and control platform 150 includes a production monitoring device. This device is used to monitor production lines. For example, the production monitoring device may include a current sensor, a temperature sensor, a gas meter, and the like. In some embodiments, the production monitoring device is deployed within an enterprise user and is configured to obtain the enterprise user's production status data.

[0039] For more information on the above, see Figure 2-Figure 4 and its related descriptions.

[0040] In some embodiments of this specification, a computing resource dynamic allocation system 100 based on an industrial Internet of Things data center can form an information operation closed loop between the industrial Internet of Things user platform and the industrial Internet of Things perception and control platform, and coordinate and operate regularly under the unified management of the industrial Internet of Things management platform, thereby realizing the informatization and intelligence of computing resource management; at the same time, the industrial Internet of Things management platform allocates computing resource configuration to different computing tasks according to the different businesses of enterprise users, which can improve the overall data quality and thus improve the service quality.

[0041] It should be noted that the above description of the dynamic allocation system for computing resources based on an industrial IoT data center 100 is for illustrative purposes only and does not limit this specification to the exemplary embodiments described. It is understood that those skilled in the art, once they understand the principles of this system, can arbitrarily combine the various platforms of this system, or form subsystems that connect to other platforms without departing from these principles.

[0042] Figure 2 This is an exemplary flow chart of a method for dynamically allocating computing resources based on an industrial Internet of Things data center according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps: In some embodiments, the process 200 may be executed by a control center.

[0043] Step 210: Receive business needs of enterprise users through the Industrial Internet of Things user platform, and send the business needs to the data computing center of the Industrial Internet of Things management platform through the Industrial Internet of Things service platform.

[0044] Enterprise users refer to organizations that need to use the computing resources of the business management sub-platform for data processing. The business management sub-platform includes multiple devices for data processing, for example, the business management sub-platform includes multiple CPUs and / or GPUs. Computing resources refer to the computing resources of the business management sub-platform. For more information about the business management sub-platform, please refer to Figure 1 For more information about computing resources, see the following description.

[0045] Business requirements refer to user demand data related to business computing and / or business processing. For example, business requirements may include business type, upload time, business volume, etc. Business volume may represent the amount of computing resources required for the current business.

[0046] In some embodiments, enterprise users input business requirements through the Industrial Internet of Things user platform. After receiving the business requirements of the enterprise users, the Industrial Internet of Things user platform sends the business requirements to the Industrial Internet of Things service platform for processing, and further sends them to the data computing center of the Industrial Internet of Things management platform.

[0047] Step 220: Monitor resource data of the business management sub-platform through the monitoring module.

[0048] The monitoring module can obtain resource data from the business management sub-platform in a variety of ways. For example, if the monitoring module is resource management software, it can remotely monitor the various performance indicators of the business management sub-platform through network protocols (such as SNMP). Alternatively, if the monitoring module is a performance counter, the performance counter can provide real-time data on system resources (such as CPU, memory, disk I / O, network traffic, etc.) and applications. The control center can then obtain resource data from the business management sub-platform based on this real-time data.

[0049] Resource data refers to data related to the computing resources of the service management sub-platform. For example, resource data includes the occupied CPUs and / or GPUs of the service management sub-platform, the available occupancy time of at least one CPU and / or GPU, etc.

[0050] Step 230: Determine the resource demand characteristics of the enterprise user based on the business needs.

[0051] Resource requirement characteristics refer to data related to the resources required to execute a particular service. For example, resource requirement characteristics include average resource requirements. Average resource requirements refer to the average number of resources required to execute the same service. Examples include the average number of CPUs and / or GPUs used and the average occupancy time of each CPU and / or GPU.

[0052] In some embodiments, the control center can determine the resource demand characteristics of enterprise users based on business needs through various methods. For example, the control center can query all historical calculation processes for such business needs according to the business needs of the enterprise users, and calculate the average resource demand of all such calculation processes as the corresponding resource demand characteristics.

[0053] In some embodiments, the resource demand characteristics also include peak characteristics, and the control center can also determine the resource demand characteristics of the enterprise user based on the production status data and business needs of the enterprise user.

[0054] Peak characteristics refer to the maximum value of computing resources used during the execution of a business, for example, the maximum number of CPUs and / or GPUs used, the maximum duration of CPU and / or GPU usage, etc.

[0055] Production status data is data that characterizes characteristics related to the production process. For example, production status data includes the current production output of the enterprise user, the number of operating production lines, product quality, etc.

[0056] In some embodiments, the production status data is acquired by a production monitoring device deployed in an enterprise user.

[0057] As an example only, when the production monitoring device is a current sensor, the current sensor monitors the current changes on the production line, and the control center can judge the product quality during the production process based on the current changes. For example, the current fluctuation of welding equipment can reflect the welding quality. For detailed description of the production monitoring device, please refer to Figure 1 The corresponding content.

[0058] In some embodiments, the control center can determine the resource demand characteristics of an enterprise user based on the enterprise user's production status data and business needs through various methods. For example, the control center can query all historical calculation processes for the type of business need and production status data of the current enterprise user, calculate the peak characteristics and average resource requirements of each of these calculation processes, sort the peak characteristics, and select the largest peak characteristic and average resource requirement as the corresponding resource demand characteristic.

[0059] In some embodiments, the control center can also determine the resource demand characteristics of enterprise users based on the production status data and business needs of enterprise users through demand estimation models. For more information about this part, please refer to Figure 3 The corresponding description.

[0060] In some embodiments of this specification, peak characteristics are taken into account to accurately control the amount and time of CPU and / or GPU required for calculations of current business needs, thereby reducing unnecessary waste of resources.

[0061] Step 240: Determine resource allocation parameters based on resource demand characteristics and resource data of the business management sub-platform.

[0062] Resource allocation parameters refer to data related to computing resources of the service management sub-platform allocated to at least one computing task.

[0063] Computational tasks refer to specific jobs or operations that need to be performed within the business management sub-platform, typically involving data processing, calculations, and analysis. The type of computational task depends on the enterprise user. For example, for a gas enterprise, computational tasks might include calculating future gas reserves and delivery volumes based on acquired data.

[0064] In some embodiments, the resource allocation parameters include the computing resources allocated to the computing task, for example, the allocated CPU and / or GPU resources, including the number of CPUs and / or GPUs and the duration of occupancy.

[0065] In some embodiments, the control center may determine resource allocation parameters in a variety of ways based on resource demand characteristics and resource data of the service management sub-platform. For example, the control center may use linear programming to determine resource allocation parameters.

[0066] For example, the objective function of linear programming is shown in the following formulas (1) and (2):

[0067] (1)

[0068] (2)

[0069] in, It represents minimizing the maximum completion time and is the objective function used to improve the computational response speed of all computing tasks; It can characterize whether the computing task (i) is assigned to the CPU (j) or GPU (j), The value of is 0 or 1. When it is 1, it means that the computing task (i) is assigned to CPU (j) or GPU (j), otherwise it is not assigned; CPU (j) and GPU (j) refer to the corresponding coding representations after the CPU and GPU are divided into coding areas, that is, the CPU of the jth coding area and the GPU of the jth coding area; represents the execution time of computing task (i) (that is, the average resource demand of the business type corresponding to the business demand i of the enterprise user in the resource demand characteristics); It represents maximizing the utilization of the shard or balancing the load. That is, it means that the computing tasks are evenly distributed among the CPUs or GPUs, while the time difference of the load tasks among the CPUs or GPUs is minimized.

[0070] The constraints corresponding to the objective function include that each computing task must be assigned to at least one coding slice, and that the load of each coding slice cannot exceed its available time. The constraint formulas are shown in the following formulas (3) and (4), where the available time of each coding slice can be determined based on the resource data obtained from the service management sub-platform:

[0071] (3)

[0072] (4)

[0073] In some embodiments, solving the objective function can be achieved through various methods, such as Pareto optimality method, ε-constraint method, etc.

[0074] In some embodiments, the control center can determine resource allocation parameters based on the computing characteristics. For more information about this part, please refer to Figure 4 The corresponding description.

[0075] Step 250: Generate resource allocation instructions according to resource allocation parameters through the control center.

[0076] Resource allocation instructions refer to the strategies and mechanisms for allocating resources.

[0077] In some embodiments, the resource allocation instruction is configured to: establish a process corresponding to the computing task according to the resource allocation parameters; bind the process corresponding to the computing task to the resource core corresponding to the computing task, and the resource core is determined based on the resource allocation parameters.

[0078] Resource cores, also known as CPU cores or GPU cores, are the basic processing units of a CPU or GPU. Each CPU core or GPU core can independently perform computing tasks, such as reading instructions, processing data, and executing programs.

[0079] In some embodiments of this specification, dynamically allocating computing resources based on the Industrial Internet of Things can effectively improve the efficiency of business processing and further improve resource utilization.

[0080] Figure 3 is an exemplary schematic diagram of a demand estimation model according to some embodiments of this specification.

[0081] In some embodiments, the control center may determine the resource demand characteristics 340 of the enterprise user based on the production status data 310 and business requirements 320 of the enterprise user and based on the demand estimation model 330 .

[0082] A demand estimation model is a model used to determine resource demand characteristics. In some embodiments, the demand estimation model can be a machine learning model, such as a recurrent neural network (RNN) model or other trained machine learning model.

[0083] In some embodiments, the input of the demand estimation model includes the production status data and business requirements of the enterprise user, and the output includes the resource demand characteristics of the enterprise user.

[0084] In some embodiments, the demand prediction model can be obtained by various methods, for example, based on multiple labeled training samples, trained by gradient descent or other feasible methods.

[0085] In some embodiments, training samples and their corresponding labels can be determined based on historical data. Training samples can be obtained based on historical data that meets expectations. The training samples may include the production status data and business needs of at least one historical enterprise user in the first historical period in the historical data that meets expectations, and the labels may be the historical resource demand characteristics actually occupied by the corresponding historical enterprise user in the second historical period. Among them, the historical data that meets expectations may be the case where the computing resources allocated to the historical enterprise user meet its computing needs, the load of the business management sub-platform is not overloaded, and the computing efficiency of the entire business management sub-platform is not lower than the preset threshold. The first historical period and the second historical period are both a period of time in the past, and the first historical period is earlier than the second historical period.

[0086] As an example, the control center can input training samples into the initial demand estimation model to obtain the output of the initial demand estimation model; construct a loss function based on the output of the initial demand estimation model and the labels corresponding to the training samples; and iteratively update the parameters of the initial demand estimation model based on the loss function. Training is completed until the iterative termination conditions are met, resulting in a trained demand estimation model. The iterative termination conditions include convergence of the loss function and the number of iterations reaching a threshold.

[0087] In some embodiments, the demand prediction model is obtained based on training of a training data set comprising a plurality of training samples. The training data set comprises a training set and a test set.

[0088] The training set is the dataset used to train the demand estimation model.

[0089] The test set is a dataset used to evaluate the demand prediction model after training is completed.

[0090] In some embodiments, the training set and the test set are determined based on the business type. For example, the control center can divide the business needs corresponding to the enterprise users and their associated production status data into multiple databases according to the business type, and randomly extract a preset proportion of samples from each of the multiple databases to the test set or the training set. The preset ratio refers to the preset ratio of samples extracted from the database to form the test set and the training set. For example, the preset ratio can be 3:7. If the extracted samples are used to form the training set, the ratio extracted from the database is 0.7. The preset ratio can be based on experience or a system default setting.

[0091] In some embodiments, among the multiple training samples, different training samples have different learning rates, and the learning rates of the training samples are related to the computational features corresponding to the training samples.

[0092] The learning rate is used to control the pace of updating the model weights when training the demand estimation model.

[0093] Computational features refer to features related to the business management sub-platform's processing of training samples. For example, computational features may include computational response speed. The computational response speed can be determined based on the time required for the business management sub-platform to complete the corresponding computational task. The longer the time required, the slower the computational response speed.

[0094] In some embodiments, the control center can determine the computing response speed of the business management sub-platform when processing various types of business needs based on the historical computing data of the business management sub-platform, and determine the average computing response speed corresponding to each type of business need as the computing feature of this type of business need, and then determine the computing feature corresponding to the training sample according to the business type corresponding to the training sample.

[0095] In some embodiments, the learning rate corresponding to the training sample is positively correlated with the corresponding computational feature.

[0096] In some embodiments of this specification, the accuracy of the obtained model can be improved by using a training data set to train and test the model; the calculation response speed is also considered when training the model, and the impact of sample quality on the model is further considered. The faster the calculation response speed, the better the quality of the training sample. In order to learn the implicit rules of such samples, the learning rate can be increased, so that the final model obtained is more in line with the actual rules.

[0097] In some embodiments of this specification, a machine learning model can be used to more accurately estimate the resources required for current computing, which is beneficial for subsequent resource allocation to improve allocation efficiency.

[0098] Figure 4 is an exemplary flow chart of determining resource allocation parameters according to some embodiments of this specification.

[0099] In some embodiments, the control center is further configured to: determine candidate parameters; determine computing characteristics corresponding to the candidate parameters based on the candidate parameters, resource demand characteristics, and resource data; and determine resource allocation parameters based on the computing characteristics.

[0100] In some embodiments, as Figure 4 As shown, the process 400 includes the following steps: The process 400 may be executed by a control center.

[0101] Step 410: Determine candidate parameters.

[0102] Candidate parameters refer to data that serve as candidate resource allocation parameters.

[0103] In some embodiments, the resource allocation parameter further includes a bandwidth adjustment amount of a network device where a communication channel of the computing task is located.

[0104] A communication channel is the medium or path for transmitting information. For example, it's the channel for obtaining business requirements corresponding to a computing task or the channel for transmitting the computational results of a computing task. The business management sub-platform can include multiple communication channels, and different computing tasks can use different communication channels for data transmission.

[0105] Bandwidth adjustment refers to the ability or mechanism to adjust the data transmission rate in network communications. Bandwidth adjustment can include, for example, the target bandwidth to be adjusted. For example, increasing the bandwidth of the network device on which a communication channel resides can increase the data transmission rate of that channel, thereby improving the execution efficiency of the computing task corresponding to that channel.

[0106] In some embodiments, the control center can determine candidate parameters in a variety of ways. For example, the control center can count the number of times each resource allocation parameter is used in historical data and select the top N resource allocation parameters with the highest number of uses as candidate parameters. The value of N can be preset as needed. For another example, the control center can randomly generate multiple resource allocation parameters as candidate parameters.

[0107] Step 420: Determine the computational characteristics corresponding to the candidate parameters based on the candidate parameters, resource demand characteristics, and resource data.

[0108] In some embodiments, the control center may determine the computational features corresponding to the candidate parameters based on the candidate parameters, resource demand characteristics, and resource data in a variety of ways. For example, the control center may determine the computational features corresponding to the candidate parameters by vector matching.

[0109] For example, the control center may construct a vector database based on historical data. The vector database may include at least one reference vector and its corresponding label.

[0110] The control center can construct at least one cluster vector based on the historical resource allocation parameters executed in the historical data, as well as the historical resource demand characteristics and historical resource data corresponding to the historical resource allocation parameters; cluster the at least one cluster vector to form a preset number of cluster centers; construct at least one reference vector based on the historical candidate parameters, historical resource demand characteristics, and historical resource data corresponding to the cluster centers; and use the historical calculation characteristics corresponding to each cluster center as the label of its corresponding reference vector. The preset number can be preset based on demand. There are many clustering algorithms, such as K-means clustering and hierarchical clustering.

[0111] In some embodiments, the control center can construct a feature vector based on the candidate parameters, resource demand characteristics, and resource data. Based on the feature vector, the control center can match the feature vector against a vector database to determine the reference vector with the highest similarity to the feature vector, and use the label of the reference vector as the calculated feature corresponding to the candidate parameter. The similarity can be determined based on vector distance; the smaller the vector distance, the higher the similarity.

[0112] In some embodiments, the control center is further configured to determine the calculation characteristics based on the candidate parameters, resource demand characteristics, and resource data through a characteristic estimation model.

[0113] In some embodiments, the calculated features also include data congestion probability and failure probability.

[0114] Data congestion probability refers to the probability that business needs need to wait for CPU and / or GPU resources to be released before they can be used.

[0115] Failure probability refers to the probability of an incident occurring during the computation process that prevents the normal execution of business requirements. For example, failure probability includes the probability of encountering problems such as hangs, insufficient memory, or excessive network transmission times during the computation process. A hang occurs when a process, program, or system temporarily stops executing or is unable to continue normal operation.

[0116] A feature prediction model is a model used to determine computational features. In some embodiments, the feature prediction model may be a machine learning model, such as a neural network (NN) model or other trained machine learning model.

[0117] In some embodiments, the input of the feature estimation model includes candidate parameters, resource demand features, and resource data, and the output includes calculated features.

[0118] In some embodiments, the feature estimation model can be obtained by various methods, for example, based on a plurality of second training samples with second labels, by training and obtaining the feature estimation model through a gradient descent method or other feasible methods.

[0119] In some embodiments, the second training sample and its corresponding second label can be determined based on historical data. The second training sample may include historical resource allocation parameters actually executed in the historical data, and the corresponding historical resource demand characteristics of at least one historical enterprise user and historical resource data of at least one historical business management sub-platform. The second label may include the historical calculation characteristics corresponding to the actual execution of the historical resource allocation parameter in the historical data. For example, the calculation response speed, data congestion probability, and failure probability of the historical resource allocation parameter when it is actually executed, where if data congestion occurs, the data congestion probability is 1, otherwise it is 0. The determination of the failure probability is similar.

[0120] The training method of the feature estimation model is similar to that of the demand estimation model, which can be found in the previous description.

[0121] Step 430: Determine resource allocation parameters based on the calculated characteristics.

[0122] In some embodiments, the control center can determine resource allocation parameters based on computing characteristics in various ways. For example, the control center can collect statistics on multiple computing characteristics and select candidate parameters corresponding to computing characteristics whose computing response speed is greater than a preset speed threshold, and whose data congestion probability and failure probability are less than preset probability thresholds, as the final resource allocation parameters. The preset speed threshold refers to the preset maximum value of the computing response speed, and the preset probability threshold refers to the preset minimum value of the data congestion probability and failure probability. The preset speed threshold and preset probability threshold can be preset based on experience or set by system default.

[0123] In some embodiments, the control center may determine the parameter evaluation value of the calculation feature based on the weighted value of the calculation response speed, data congestion probability, and failure probability of the calculation feature; and determine the resource allocation parameter based on the parameter evaluation value of the calculation feature.

[0124] The parameter evaluation value can represent the comprehensive performance evaluation result of the resource allocation parameter. The larger the parameter evaluation value, the more preferentially the resource allocation parameter should be applied. For example, the control center can select the candidate parameter corresponding to the calculation feature with the largest parameter evaluation value as the resource allocation parameter.

[0125] In some embodiments, the control center can obtain weighted values of the calculation response speed, data congestion probability, and failure probability of the calculation feature through various methods. For example, the control center can obtain the aforementioned weighted values through a preset formula. For example, the preset formula is shown in the following formula (5):

[0126] (5)

[0127] in, represents the weighted value, Indicates the calculation response speed, represents the probability of data congestion, represents the probability of failure, 、 、 is the preset coefficient. 、 、 Can be preset based on experience.

[0128] In some embodiments, the weighted values of the computational response speed, data congestion probability, and failure probability of the computational characteristics are related to the resource demand characteristics of the enterprise user, that is, 、 、 It can be determined based on the resource demand characteristics of enterprise users.

[0129] In some embodiments, the greater the average resource demand in the resource demand characteristics of the enterprise user, The smaller the data volume, the greater the difference between the total data volume of the business needs of enterprise users and the available computing resources of the business management sub-platform. The smaller it is; the larger the total amount of data required by enterprise users, The smaller.

[0130] In some embodiments of this specification, by associating each weight with the resource demand characteristics of the enterprise user, the obtained weighted value can be made more accurate, and the resource allocation parameters subsequently determined can be more in line with the actual situation.

[0131] In some embodiments of this specification, the computing response speed, data congestion probability, and failure probability are estimated through a machine learning model, which can ensure the accuracy of the acquired computing features and reduce the time wasted in the estimation process; the parameter evaluation value is determined based on the weighted value of each item of the computing feature, and then the resource allocation parameter is determined, which is conducive to finding the best solution, thereby effectively improving the actual service effect.

[0132] In some embodiments, the resource allocation instruction is configured to: obtain communication information of the computing task; determine the communication channel of the computing task based on the communication information; adjust the bandwidth allocation policy of the network device where the communication channel of the computing task is located based on the bandwidth adjustment amount corresponding to the communication channel in the resource allocation parameters, so as to adjust the bandwidth of the communication channel of the computing task.

[0133] Communication information refers to data related to the communication of the business requirements in the computing task. In some embodiments, the communication information includes at least one of a communication source address, a communication destination address, and a communication transit address corresponding to the computing task.

[0134] The communication source address refers to the address of the device or node that sends information in the network. For example, the address of the device or node that sends a business request in the network.

[0135] The communication destination address is the address of the target device or node to which the information is sent. For example, the address of the target device or node to which the calculation result is sent.

[0136] The communication transit address refers to the address of the intermediate device or node that the data may pass through during the transmission process from the source address to the destination address.

[0137] In some embodiments, when a process is created, the control center can directly obtain communication information based on business needs.

[0138] In some embodiments, the control center determines the communication channel for each computing task by querying the routing table on the network device based on the communication source address, destination address, and transit address of each computing task. A network device is an electronic device used to connect and manage computers and other devices in a network to enable data transmission, communication, and network services. A routing table is a data structure on a network device that stores path information. The routing table records the destination address of data transmission, the address of the next network device, and other information. The routing table can be manually configured by a staff member or automatically updated by a dynamic routing protocol. A dynamic routing protocol is a mechanism for automatically discovering and maintaining routing information in a computer network.

[0139] A bandwidth allocation policy is the method and rules used to allocate available bandwidth to different users, devices, or applications within a network. For example, a bandwidth allocation policy might include the bandwidth allocation amount and allocation priority for each network device on which a communication channel resides. A bandwidth allocation policy can be determined in any feasible manner.

[0140] In some embodiments, the control center adjusts the bandwidth of the communication channel of each task by adjusting the bandwidth allocation policy of the network device where the communication channel of each task is located according to the bandwidth adjustment amount corresponding to the communication channel of each task in the resource allocation parameters. For example, the corresponding bandwidth allocation amount in the bandwidth allocation policy of the network device where the communication channel is located is increased to the corresponding bandwidth adjustment amount in the resource allocation parameters.

[0141] In some embodiments of the present specification, by generating multiple candidate parameters and evaluating the actual calculation characteristics of each candidate parameter, an optimal solution is determined, thereby effectively improving the actual service effect.

[0142] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0143] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0144] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0145] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0146] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may vary according to the required features of the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values are as accurate as possible within the feasible range.

[0147] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This excludes any application history documents that are inconsistent with or conflicting with the content of this specification, as well as any documents (currently or subsequently appended to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0148] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A dynamic allocation system for computing resources based on an industrial Internet of Things data center, characterized in that: The system includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, an industrial Internet of Things management platform, an industrial Internet of Things sensor network platform and an industrial Internet of Things perception control platform; The industrial Internet of Things user platform is configured to receive business needs of enterprise users and send the business needs to the data computing center of the industrial Internet of Things management platform through the industrial Internet of Things service platform; The industrial Internet of Things management platform includes the data computing center, the business management sub-platform and the control center; the business management sub-platform includes a monitoring module, and the monitoring module is configured to monitor the resource data of the business management sub-platform; The control center is configured to: Determining resource demand characteristics of the enterprise user based on the business needs; Determining resource allocation parameters based on the resource demand characteristics and the resource data of the business management sub-platform; the resource allocation parameters include computing resources corresponding to the computing task; The control center is further configured to generate a resource allocation instruction according to the resource allocation parameter; the resource allocation instruction is configured to: Establishing a process corresponding to the computing task; The process corresponding to the computing task is bound to a resource core corresponding to the computing task, where the resource core is determined based on the resource allocation parameter.

2. The system according to claim 1, wherein The industrial Internet of Things perception control platform further includes a production monitoring device, which is deployed in the enterprise user and is configured to obtain production status data of the enterprise user; The resource demand characteristics also include peak characteristics; The control center is further configured to: The resource demand characteristics of the enterprise user are determined based on the production status data and the business needs of the enterprise user.

3. The system according to claim 2, wherein: The control center is further configured to determine the resource demand characteristics of the enterprise user based on the production status data and the business needs of the enterprise user and based on a demand prediction model, and the demand prediction model is a machine learning model.

4. The system according to claim 1, wherein: The resource allocation parameters also include a bandwidth adjustment amount of the network device where the communication channel of the computing task is located; the control center is further configured to: Determine candidate parameters; Determining a calculation feature corresponding to the candidate parameter based on the candidate parameter, the resource demand feature, and the resource data; determining the resource allocation parameter based on the calculation characteristics; The resource allocation instruction is configured to: Acquire communication information of the computing task, the communication information including at least one of a communication source address, a communication destination address, and a communication transit address; determining a communication channel for the computing task according to the communication information; According to the bandwidth adjustment amount corresponding to the communication channel in the resource allocation parameter, the bandwidth allocation policy of the network device where the communication channel of the computing task is located is adjusted to adjust the bandwidth of the communication channel of the computing task.

5. The system according to claim 4, wherein: The computing characteristics include computing response speed, data congestion probability and failure probability; The control center is further configured to: Determining the computational features through a feature estimation model based on the candidate parameters, the resource demand features, and the resource data, wherein the feature estimation model is a machine learning model; determining a parameter evaluation value of the calculation feature based on a weighted value of the calculation response speed, the data congestion probability, and the failure probability of the calculation feature; The resource allocation parameter is determined based on the parameter evaluation value of the calculation characteristic.

6. A method for dynamically allocating computing resources based on an industrial Internet of Things data center, characterized in that: The method is executed by a control center of an industrial Internet of Things management platform of a computing resource dynamic allocation system based on an industrial Internet of Things data center, wherein the system includes an industrial Internet of Things user platform, an industrial Internet of Things service platform, the industrial Internet of Things management platform, an industrial Internet of Things sensor network platform, and an industrial Internet of Things perception control platform; The industrial Internet of Things management platform includes a data computing center, a business management sub-platform and the control center; The business management sub-platform includes a monitoring module; The method comprises: Receiving business needs of enterprise users through the Industrial Internet of Things user platform, and sending the business needs to the data computing center of the Industrial Internet of Things management platform through the Industrial Internet of Things service platform; Monitoring resource data of the business management sub-platform through the monitoring module; Determining resource demand characteristics of the enterprise user based on the business needs; Determining resource allocation parameters based on the resource demand characteristics and the resource data of the business management sub-platform; the resource allocation parameters include computing resources corresponding to the computing task; Generate a resource allocation instruction according to the resource allocation parameters by the control center; the resource allocation instruction is configured to: Establishing a process corresponding to the computing task; The process corresponding to the computing task is bound to a resource core corresponding to the computing task, where the resource core is determined based on the resource allocation parameter.

7. The method according to claim 6, wherein The resource demand characteristics also include peak characteristics. Determining the resource demand characteristics of the enterprise user based on the business demand includes: The resource demand characteristics of the enterprise user are determined based on the production status data of the enterprise user and the business demand; wherein the production status data is obtained by a production monitoring device deployed in the enterprise user.

8. The method according to claim 7, wherein The determining the resource demand characteristics of the enterprise user based on the production status data and the business needs of the enterprise user includes: Based on the production status data and business needs of the enterprise user and based on a demand prediction model, the resource demand characteristics of the enterprise user are determined, and the demand prediction model is a machine learning model.

9. The method according to claim 6, wherein The resource allocation parameter also includes a bandwidth adjustment amount of the network device where the communication channel of the computing task is located. The determining of the resource allocation parameter based on the resource demand characteristics and the resource data of the service management sub-platform includes: Determine candidate parameters; Determining a calculation feature corresponding to the candidate parameter based on the candidate parameter, the resource demand feature, and the resource data; determining the resource allocation parameter based on the calculation characteristics; The resource allocation instruction is configured to: Acquire communication information of the computing task, the communication information including at least one of a communication source address, a communication destination address, and a communication transit address; determining a communication channel for the computing task according to the communication information; According to the bandwidth adjustment amount corresponding to the communication channel in the resource allocation parameter, the bandwidth allocation policy of the network device where the communication channel of the computing task is located is adjusted to adjust the bandwidth of the communication channel of the computing task.

10. The method according to claim 9, wherein The calculation characteristics include calculation response speed, data congestion probability, and failure probability; and determining the resource allocation parameters based on the calculation characteristics includes: Determining the computational features through a feature estimation model based on the candidate parameters, the resource demand features, and the resource data, wherein the feature estimation model is a machine learning model; determining a parameter evaluation value of the calculation feature based on a weighted value of the calculation response speed, the data congestion probability, and the failure probability of the calculation feature; The resource allocation parameter is determined based on the parameter evaluation value of the calculation characteristic.

Images