Method and apparatus for parallel deployment of multiple services, electronic device and storage medium

Abstract

The present disclosure relates to a method and apparatus for parallel deployment of multiple services, an electronic device and a storage medium. A method for parallel deployment of multiple services on an edge device comprises: setting a configuration file of the edge device in the format of a preset configuration template, the configuration file comprising related information of the edge device, related information of services to be deployed in parallel on the edge device, and information of an event for triggering service replacement; parsing the configuration file; on the basis of parsed deployment information, creating a space for service deployment, a data input channel and a data transmission channel, to deploy on the edge device multiple services running in parallel; and monitoring the multiple services running in parallel.

Description

Method, device, electronic device and storage medium for parallel deployment of multiple services Technical Field

[0001] The present disclosure generally relates to the field of edge device technology, and more particularly, to a method, apparatus, electronic device, and storage medium for deploying multiple services in parallel on an edge device. Background Art

[0002] With the growing emphasis on edge management, many companies have launched edge management frameworks in recent years, and some small and medium-sized enterprises have opted for open source framework solutions. These products and frameworks can help manage edge devices, data, and algorithm model deployment, but they present the following challenges for deploying multiple models / applications in parallel:

[0003] 1. Parallel configuration is difficult and limited by device performance. Based on the existing framework and management model, one model corresponds to one container unit. Parallel configuration leads to confusion in module and task lists and limits the performance of edge devices.

[0004] 2. Increased resource and bandwidth overhead. Parallel deployment aims to select a better edge strategy, but it does result in increased bandwidth consumption. How to achieve this while saving costs is a challenge.

[0005] Currently, there is no convenient framework to support parallel mode. In some cases, a distributed training mode can be built through a distributed cluster environment, but it consumes a lot of resources.

[0006] The typical remedy is to open multiple deployment containers based on the existing edge management framework, while also considering the performance support of edge devices to make each module relatively independent. This also requires manual operation and maintenance by maintenance engineers through instructions.

[0007] Summary of the Invention

[0008] A brief overview of the present invention is provided below to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important aspects of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is simply to present certain concepts in a simplified form as a prelude to the more detailed description discussed later.

[0009] In view of this, the present disclosure proposes a method for deploying multiple services in parallel on an edge device for an edge side.

[0010] According to one aspect of the present disclosure, a method for deploying multiple services in parallel on an edge device is provided, comprising:

[0011] Setting a configuration file for the edge device in a format of a preset configuration template, wherein the configuration file includes information related to the edge device, information related to services to be deployed in parallel on the edge device, and information about events that trigger service replacement;

[0012] Parsing the configuration file;

[0013] Creating a space for deploying services, a data input channel, and a data transmission channel based on the deployment information obtained by parsing, thereby deploying multiple services running in parallel on the edge device;

[0014] The multiple services running in parallel are monitored.

[0015] In this way, a scalable parallel configuration channel can be provided for multiple services. Edge devices can download the corresponding program packages and make the operating environment consistent, avoiding the construction of complex container nodes and transmission data space, thereby saving resources.

[0016] Optionally, in an example of the above aspect, the method further includes: judging whether a preset replacement condition is met based on the data obtained through monitoring, and if so, deleting the space for deploying the related service.

[0017] In this way, more efficient services can be retained and less efficient services can be removed.

[0018] Optionally, in an example of the above aspect, the deployment information includes: system image requirements, program package requirements and link relationships, variables and their attributes, replacement rules and events.

[0019] Optionally, in an example of the above aspect, deploying multiple services running in parallel on the edge device includes:

[0020] determining whether the system image requirements are the same; if so, merging the same system image requirements and creating a space for deploying services based on the system image requirements; and if the system image requirements are different, creating spaces for deploying services respectively for different system image requirements;

[0021] Determine whether the package requirements are the same. If they are the same, merge the same package requirements and create a package download channel. If they are different, create separate package download channels for different package requirements.

[0022] Determine whether a parallel relationship is set. If so, merge the input variables, check the output variables, create a data subscription channel, and set a shared time period. If not, merge the input variables and output variables with the same attributes, and then create a data subscription channel.

[0023] In this way, based on the analysis of the configuration file, a parallel operation mode is constructed, and a unified input data channel and transmission data channel are used to save operation resources and data training units.

[0024] Optionally, in an example of the above aspect, the preset replacement condition includes at least one of the following: a replacement event based on time, a replacement event based on a value, a replacement event based on a comparison result, etc.

[0025] According to another aspect of the present disclosure, an apparatus for deploying multiple services in parallel on an edge device is provided, comprising:

[0026] a configuration file setting unit configured to set a configuration file for the edge device according to a format of a preset configuration template, wherein the configuration file includes information related to the edge device, information related to services to be deployed in parallel on the edge device, and information about events that trigger service replacement;

[0027] a configuration file parsing unit, configured to parse the configuration file;

[0028] A service deployment unit is configured to create a space for deploying services, a data input channel, and a data transmission channel based on the deployment information obtained by parsing, thereby deploying multiple services running in parallel on the edge device;

[0029] The monitoring unit is configured to monitor the multiple services running in parallel. In this way, resource allocation and application execution can be performed on each distributed device, and performance indicators of each application can be collected as a reference for adjusting configuration parameters.

[0030] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory coupled to the at least one processor, the memory being used to store instructions that, when executed by the at least one processor, enable the processor to execute the method described above.

[0031] According to another aspect of the present disclosure, a non-transitory machine-readable storage medium is provided, which stores executable instructions. When the instructions are executed, the machine is caused to perform the method described above.

[0032] According to another aspect of the present disclosure, a computer program product is provided, which is tangibly stored on a computer-readable medium and includes computer-executable instructions that, when executed, cause at least one processor to perform the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other purposes, features and advantages of the present invention will be more easily understood by referring to the following description of the embodiments of the present invention in conjunction with the accompanying drawings. The components in the accompanying drawings are only for illustrating the principles of the present invention. In the accompanying drawings, the same or similar technical features or components will be represented by the same or similar reference numerals. In the accompanying drawings:

[0034] FIG1 is a schematic architecture diagram of an edge system;

[0035] FIG2 is a flowchart of an exemplary process of a method for deploying multiple services in parallel on an edge device according to an embodiment of the present disclosure;

[0036] FIG3 is a block diagram illustrating an exemplary configuration of an apparatus for deploying multiple services in parallel on an edge device according to another embodiment of the present disclosure;

[0037] FIG4 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

[0038] The reference numerals are as follows: 10: edge system 102: server or cloud platform 104-1, 104-2, ... 104-n: edge device 106-1, 106-2: model 108-1, 108-2, 108-3: application 200: method for deploying multiple services in parallel on an edge device S202, S204, S206, S208, S210: step 300: apparatus for deploying multiple services in parallel on an edge device 302: configuration file setting unit 304: configuration file parsing unit 306: service deployment unit 308: monitoring unit 310: service deletion unit 400: electronic device 402: processor 404: memory DETAILED DESCRIPTION

[0039] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that discussing these embodiments is intended only to enable those skilled in the art to better understand and implement the subject matter described herein, and is not intended to limit the scope of protection, applicability, or examples set forth in the claims. The functions and arrangements of the elements discussed may be changed without departing from the scope of protection of this disclosure. Various examples may omit, replace, or add various processes or components as needed. For example, the described method may be performed in an order different from the described order, and various steps may be added, omitted, or combined. In addition, features described relative to some examples may also be combined in other examples.

[0040] As used herein, the term "including" and its variations are open terms meaning "including but not limited to". The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other definitions may be included below, whether explicit or implicit. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout the specification.

[0041] Currently, practical application scenarios for deploying multiple models / applications in parallel may include the following requirements:

[0042] During the design phase, simulation software typically runs tests using a single model (including complex parameters). Being able to run multiple models in parallel and compare them would save time and effort.

[0043] During the on-site debugging phase, multiple models / applications can be run in parallel at the edge, and the best model / application can be selected after verifying their effectiveness.

[0044] During maintenance or upgrades, multiple applications can be run in parallel. After confirming the performance, the application with better performance can be selected for seamless replacement.

[0045] According to the technical solution of the present disclosure, a method for deploying multiple services in parallel on an edge device is proposed for an edge device on the edge side.

[0046] The services described here may include algorithms, models, applications, etc. deployed on edge devices. The "services" mentioned in this article may refer to any of the algorithms, models, applications, etc., and are not limited to these.

[0047] The following describes a method and apparatus for deploying multiple services in parallel on an edge device according to an embodiment of the present disclosure in conjunction with the accompanying drawings.

[0048] FIG1 is a schematic architecture diagram of an edge system 10. The edge system includes a server or cloud platform 102 and multiple edge devices 104 - 1, 104 - 2, ..., 104 - n. Two models 106 - 1 and 106 - 2 are deployed on edge device 104 - 1, running in parallel. Three applications 108 - 1, 108 - 2, and 108 - 3 are deployed on edge device 104 - 2, running in parallel.

[0049] Users can deploy multiple models, applications, or algorithms in parallel on edge devices as needed.

[0050] FIG2 is a flowchart of an exemplary process of a method 200 for deploying multiple services in parallel on an edge device according to an embodiment of the present disclosure. The method specifically includes:

[0051] First, in step S202 , a configuration file of the edge device is set according to the format of a preset configuration template.

[0052] In an embodiment of the present disclosure, a standard template for a configuration file of an edge device is pre-set, and the configuration file of the edge device is set according to the format of the template.

[0053] The template of the configuration file may include information related to the edge device, information related to services to be deployed in parallel on the edge device, and information about events that trigger service replacement.

[0054] In a specific embodiment, the template of the configuration file may include the following information.

[0055] Among them, the relevant information of the edge device includes device name, device address, system image and other information.

[0056] The system image refers to the operating environment of the edge device, such as Windows, Linux, etc. The system image can include information such as the image name, image version, image file, and resource description.

[0057] The information related to the services to be deployed in parallel on the edge devices may include the corresponding instances set for the applications or algorithms to be deployed. Each instance may include: instance name, package, link relationship, and monitoring rules.

[0058] A program package is a service program and may include a program name, a program package file, and data parameters (input parameters, output parameters, etc.).

[0059] The link relationship includes information such as the algorithm / program instance with the link relationship, the parallel time period, the link status, and the link unbinding.

[0060] Rules refer to the rules used when monitoring each service, which can include heartbeat alarms, monitoring value alarms, regression comparisons, and other information.

[0061] Service replacement refers to the removal of one of the parallel services when a preset event is met. Events that trigger service replacement can include replacement events and comparison events. Replacement events include rules such as setting a replacement time or parameter thresholds for replacement. Comparison events include setting comparison parameters, setting a comparison cycle time, and performing performance comparisons. The events that trigger service replacement are described in detail below.

[0062] It is understandable that the information included in the configuration file template can be set according to user needs, can be reduced or further expanded, and is not limited to the specific information described above.

[0063] By defining a template for such a configuration file, users can easily set up multiple parallel services on edge devices, and automatically replace services that do not meet the requirements, which helps users manage multiple edge devices.

[0064] The above configuration file can be set on the edge device, or it can be a configuration file that meets the configuration template format received from a server or cloud platform, which is not described in detail in this disclosure.

[0065] Next, in step S204, the configuration file is parsed.

[0066] Specifically, the deployment information extracted by parsing the configuration file may include, for example, system image requirements, program package requirements and link relationships, variables and their attributes, replacement rules and events, and other information.

[0067] Next, in step S208 , a space (or node) for deploying services, as well as a data input channel and a data transmission channel, is created based on the deployment information obtained through parsing, thereby deploying multiple services running in parallel on one edge device.

[0068] Specifically, first determine whether the system image requirements are the same. If they are the same, merge the same system image requirements and create a space for deploying services based on the system image requirements. If the system image requirements are different, create a space for deploying services separately for different system image requirements.

[0069] Next, determine whether the package requirements are the same. If they are the same, merge the same package requirements and create a package download channel. If they are different, create separate package download channels for different package requirements.

[0070] Determine whether a parallel relationship is set. If so, merge the input variables, check the output variables, create a data subscription channel, and set a shared time period. If not, merge the input variables and output variables with the same attributes, and then create a data subscription channel.

[0071] Through the above operations, multiple services running in parallel can be deployed on one edge device.

[0072] Multiple services running in parallel can share an input port to collect physical data. At the output port of the data channel, the same data source can be sent to multiple parallel instances by adding a shared target parallel instance.

[0073] In this process, identical resource requirements are merged, thus conserving resources and enabling comparison of services running in parallel.

[0074] Next, in step S208 , the multiple services running in parallel are monitored.

[0075] Multiple services can run in parallel on an edge device, and if certain predetermined conditions are met, one or more of the services can be deleted, thereby monitoring multiple services. Specifically, for example, multiple services can be monitored based on preset rules, events, performance, etc.

[0076] In one example, the method 200 may further include step S210: determining whether a preset replacement condition is met based on the monitored data, and if so, deleting the space (or node) where the related service is deployed.

[0077] The preset replacement conditions may include a replacement event based on time, a replacement event based on a value, a replacement event based on a comparison result, and the like.

[0078] Time-based replacement events include, for example, how long the service deployment takes, or when to set the replacement.

[0079] Value-based replacement events include, for example, scores obtained from algorithm training, input / output values ​​reaching preset values, etc.

[0080] Replacement events based on the comparison results can include:

[0081] Comparison parameters, such as comparing output values ​​of various services, may be performed to determine if the result exceeds a specific threshold.

[0082] Compare cycle times. Set different cycle times to check the comparison of different time windows. This way, you can get a judgment conclusion based not only on a single comparison result.

[0083] Performance comparison, such as setting replacement events based on performance comparison and marginal resource consumption.

[0084] Those skilled in the art can set appropriate replacement events as needed, and when monitoring determines that a certain replacement event is met, the space where the related services are deployed can be deleted. The related services refer to the services involved in the replacement event.

[0085] For example, based on a replacement event of a comparison result, the performance of service A and service B is compared. If it is determined that the performance of service A is better than that of service B, the space where service B is deployed is deleted. Here, service B is the relevant service.

[0086] The method disclosed herein supports parallel deployment of multiple services and builds link relationships between services, helping users to compare services conveniently.

[0087] According to the method disclosed in the present invention, a scalable parallel configuration channel can be provided for multiple services, edge devices can download corresponding program packages, and make the operating environment consistent, which can avoid building complex container nodes and transmitting data space, thereby saving resources.

[0088] According to the method disclosed herein, a parallel operation mode is constructed based on the analysis of the configuration file, and the parallel units are monitored at the same time; by utilizing a unified input data channel and a transmission data channel, operation resources and data training units can be saved.

[0089] In addition, the method according to the present disclosure may also support data storage and data communication, and data storage may support offline or tracking comparison needs.

[0090] According to the method disclosed in the present invention, more efficient services can be selected and retained, and less efficient services can be deleted based on the comparison of multiple services running in parallel.

[0091] FIG3 is a block diagram of an exemplary configuration of an apparatus 300 for deploying multiple services in parallel on an edge device according to another embodiment of the present disclosure. The apparatus 300 is configured to execute the method for deploying multiple services in parallel on an edge device as shown in FIG2 . The apparatus 300 may be provided on each edge device.

[0092] The apparatus 300 for deploying multiple services in parallel on an edge device shown in FIG3 includes a configuration file setting unit 302 , a configuration file parsing unit 304 , a service deployment unit 306 , and a monitoring unit 308 .

[0093] The configuration file setting unit 302 is configured to set a configuration file for the edge device according to a format of a preset configuration template. The configuration file includes information about the edge device, information about services to be deployed in parallel on the edge device, and information about events that trigger service replacement.

[0094] The configuration file parsing unit 304 is configured to parse the configuration file.

[0095] The service deployment unit 306 is configured to create a space for deploying services, a data input channel, and a data transmission channel based on the deployment information obtained by parsing, thereby deploying multiple services running in parallel on the edge device.

[0096] The monitoring unit 308 is configured to monitor the multiple services running in parallel.

[0097] In one example, the apparatus 300 for deploying multiple services in parallel on an edge device further includes a service deletion unit 310 configured to determine whether a preset replacement condition is met based on data obtained through monitoring, and if so, to delete the space for deploying related services.

[0098] The details of the operations and functions of the various parts of the apparatus 300 for deploying multiple services in parallel on an edge device may be the same as or similar to the relevant parts of the embodiment of the method for deploying multiple services in parallel on an edge device of the present disclosure described with reference to FIG1-2 , and will not be described in detail here.

[0099] It should be noted that the structure of the apparatus 300 for deploying multiple services in parallel on an edge device and its constituent units shown in FIG3 is merely exemplary, and those skilled in the art may modify the structural block diagram shown in FIG3 as needed.

[0100] The method and apparatus according to the embodiments of the present disclosure are described above with reference to Figures 1 to 3. Each unit of the apparatus for deploying multiple services in parallel on an edge device described above can be implemented using hardware, software, or a combination of hardware and software.

[0101] 4 shows a block diagram of an electronic device 400 according to an embodiment of the present disclosure. According to one embodiment, the electronic device 400 may include at least one processor 402 that executes at least one computer-readable instruction stored or encoded in a computer-readable storage medium (ie, memory 404).

[0102] It should be understood that the computer executable instructions stored in the memory 404, when executed, cause the at least one processor 402 to perform the various operations and functions described above in conjunction with Figures 1-3 in various embodiments of the present disclosure.

[0103] According to one embodiment, a non-transitory machine-readable medium is provided. The non-transitory machine-readable medium may have machine-executable instructions, which, when executed by a machine, enable the machine to perform various operations and functions described above in conjunction with Figures 1-3 in various embodiments of the present disclosure.

[0104] According to one embodiment, a computer program is provided, including computer-executable instructions, which, when executed, enable at least one processor to perform the various operations and functions described above in conjunction with Figures 1-3 in various embodiments of the present disclosure.

[0105] According to one embodiment, a computer program product is provided, including computer-executable instructions, which, when executed, enable at least one processor to perform the various operations and functions described above in conjunction with Figures 1-3 in various embodiments of the present disclosure.

[0106] It should be understood that the various embodiments in this specification are described in a progressive manner, and reference can be made to the identical or similar parts of the various embodiments. Each embodiment focuses on the differences from the other embodiments. For example, the aforementioned apparatus embodiments, electronic device embodiments, and machine-readable storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant details, reference can be made to the descriptions of the method embodiments.

[0107] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] Not all steps and units in the above processes and system structure diagrams are required, and some steps or units may be omitted according to actual needs. The device structures described in the above embodiments can be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or may be implemented by certain components in multiple independent devices.

[0109] The specific embodiments described above in conjunction with the accompanying drawings describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of protection of the claims. The term "exemplary" used throughout this specification means "used as an example, instance, or illustration" and does not mean "preferred" or "having advantages" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, these technologies can be implemented without these specific details. In some instances, in order to avoid obscuring the concepts of the described embodiments, well-known structures and devices are shown in block diagram form.

[0110] The foregoing description of the present disclosure is provided to enable any person skilled in the art to implement or use the present disclosure. Various modifications to the present disclosure will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is intended to be consistent with the widest range of principles and novel features disclosed herein.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0112] Nouns and pronouns referring to persons in this patent application are not limited to a specific gender.

Claims

1. A method (200) for parallelly deploying multiple services on an edge device, comprising: Setting a configuration file of the edge device according to the format of a preset configuration template, where the configuration file includes information related to the edge device, information related to the services to be parallelly deployed on the edge device, and information about events triggering service replacement (S202); Parsing the configuration file (S204); Creating a space for deploying services, a data input channel, and a data transmission channel based on the deployment information obtained from the parsing, so as to deploy multiple services running in parallel on the edge device (S206); Monitoring the multiple services running in parallel (S208).

2. The method (200) according to claim 1, further comprising: Judging whether the preset replacement conditions are met according to the data obtained from the monitoring, and if so, deleting the space for the services related to the deployment (S210).

3. The method (200) according to claim 1, wherein The deployment information includes: system image requirements, package requirements and link relationships, variables and their attributes, replacement rules, and events.

4. The method (200) according to claim 3, wherein Deploying multiple services running in parallel on the edge device includes: Judging whether the system image requirements are the same. If they are the same, merging the same system image requirements and creating a space for deploying services based on the system image requirements. If the system image requirements are different, creating spaces for deploying services respectively for different system image requirements; Judging whether the package requirements are the same. If they are the same, merging the same package requirements and creating a package download channel. If they are different, creating package download channels respectively for different package requirements; Judging whether a parallel relationship is set. If so, merging the input variables, checking the output variables, creating a data subscription channel, and setting a shared time period. If not, merging the input variables and output variables with the same attributes and then creating a data subscription channel.

5. The method (200) according to claim 3, wherein, The preset replacement conditions include at least one of the following: time-based replacement events, value-based replacement events, and comparison result-based replacement events, etc.

6. An apparatus (300) for parallelly deploying multiple services on an edge device, comprising: A configuration file setting unit (302), configured to set a configuration file of the edge device according to the format of a preset configuration template, where the configuration file includes information related to the edge device, information related to the services to be parallelly deployed on the edge device, and information about events triggering service replacement; A configuration file parsing unit (304), configured to parse the configuration file; A service deployment unit (306), configured to create a space for deploying services, a data input channel, and a data transmission channel based on the deployment information obtained from the parsing, so as to deploy multiple services running in parallel on the edge device; A monitoring unit (308), configured to monitor the multiple services running in parallel.

7. The apparatus (300) according to claim 6, further comprising: A service deletion unit (310), configured to judge whether the preset replacement conditions are met according to the data obtained from the monitoring, and if so, deleting the space for the services related to the deployment.

8. An electronic device (400), comprising: at least one processor (402); and a memory (404) coupled to the at least one processor (402), the memory being configured to store instructions that, when executed by the at least one processor (402), cause the processor (402) to perform the method according to any one of claims 1-5.

9. A non-transitory machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the method according to any one of claims 1-5.

10. A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause at least one processor to perform the method according to any one of claims 1-5.

Images