An edge computing resource scheduling method, apparatus, device, and readable storage medium

Abstract

The present invention discloses an edge computing resource scheduling method, which generates corresponding custom computer room pre-selection strategies and custom host pre-selection strategies according to the computing power demands of different clients, thereby determining a target computer room that meets user needs from the optional computer rooms according to the strategy, and selecting a target host that meets user needs from the target computer room, thereby scheduling the best computing power resources of the optimal node that meets the client's demands, adapting to the changing user business scenarios, and using the screened target host as the scheduling result, responding to user needs, and improving user service quality. The present invention also discloses an edge computing resource scheduling device, equipment, and readable storage medium, which have corresponding technical effects.

Description

Technical Field

[0001] The present invention relates to the field of edge computing technology, and in particular to an edge computing resource scheduling method, device, equipment and readable storage medium. Background Art

[0002] Edge computing refers to a distributed, open platform that integrates core networking, computing, storage, and application capabilities at the edge of the network, close to the source of objects or data, to provide localized edge intelligent services. Edge computing nodes are closer to user terminals and can quickly respond to their computing requests, ensuring high-latency services.

[0003] With the development of edge computing services, edge computing business scenarios are becoming more and more diverse. The current scheduling system is unable to meet the diverse demands of different clients for computing resources in different business scenarios.

[0004] To sum up, how to flexibly adapt to support the computing power demands of flexible and changing business scenarios is a technical problem that technical personnel in this field urgently need to solve. Summary of the Invention

[0005] The purpose of the present invention is to provide an edge computing resource scheduling method, device, equipment and readable storage medium that can meet the computing power requirements of diverse business scenarios.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A method for scheduling edge computing resources, comprising:

[0008] Receive computing resource scheduling requests initiated by clients;

[0009] Generate a custom computer room pre-selection strategy based on the user's demand information for the computer room in the computing resource scheduling request, and generate a custom host pre-selection strategy based on the user's demand information for the host;

[0010] Screening the computer rooms according to the self-defined computer room pre-selection strategy to determine the target computer room to be called;

[0011] Perform host screening in the target computer room according to the custom host pre-selection policy to determine the target host to be called;

[0012] The target host is called to provide computing services for the client.

[0013] Optionally, screening the computer rooms according to the customized computer room pre-selection strategy to determine the target computer room to be called includes:

[0014] Call the preset general computer room pre-selection strategy to filter out available computer rooms from the optional computer rooms;

[0015] The customized computer room pre-selection strategy is called to select a computer room that meets the user's customized requirements from the available computer rooms as the target computer room to be called.

[0016] Optionally, after calling the customized computer room pre-selection strategy to select a computer room that meets the user customized requirements from the available computer rooms, the method further includes:

[0017] Determine whether the computer room that meets the user's customized requirements is unique;

[0018] If so, the computer room that meets the user's customized requirements is used as the target computer room to be called;

[0019] If not, calculate the priority of the computer room call that meets the user's customized requirements;

[0020] The target computer room to be called is determined according to the order of the priorities from high to low.

[0021] Optionally, calculating the priority of the computer room call that meets the user-defined requirements includes:

[0022] The priority of the computer room call is evaluated based on the physical distance from the client and the load of the computer room itself.

[0023] Optionally, the method for determining the physical location distance includes:

[0024] Determine whether the latitude and longitude information of the client can be obtained;

[0025] If available, calculate the physical distance between the computer room and the client based on the latitude and longitude information of the client and the latitude and longitude information of each computer room;

[0026] If unavailable, determine the IP address of the client;

[0027] Resolve the operating city corresponding to the IP address;

[0028] The central longitude and latitude of the operating city are used as the longitude and latitude information of the client, and the step of calculating the physical location distance between the computer room and the client based on the longitude and latitude information of the client and the longitude and latitude information of each computer room is performed.

[0029] Optionally, receiving a computing resource scheduling request initiated by a client includes:

[0030] Receive user-specified application requirements sent by the client;

[0031] Determine computing power demand information corresponding to the user-specified application requirements;

[0032] A scheduling request is generated according to the computing power demand information as the computing power resource scheduling request.

[0033] Optionally, before receiving the computing resource scheduling request initiated by the client, the method further includes:

[0034] Setting attribute tags for each optional computer room according to the attribute information of the optional computer room;

[0035] Setting attribute tags for each optional host according to the attribute information of the optional host;

[0036] Accordingly, screening the computer rooms according to the self-defined computer room pre-selection strategy to determine the target computer room to be called includes: screening the computer rooms according to the self-defined computer room pre-selection strategy and comparing the attribute tags corresponding to the optional computer rooms to determine the target computer room to be called;

[0037] Performing host screening in the target computer room according to the custom host pre-selection policy to determine the target host to be called includes: performing host screening by comparing the attribute tags corresponding to each host in the target computer room according to the custom host pre-selection policy to determine the target host to be called.

[0038] An edge computing resource scheduling device, comprising:

[0039] A request receiving unit, configured to receive a computing resource scheduling request initiated by a client;

[0040] A strategy generating unit, configured to generate a customized computer room pre-selection strategy based on the user's demand information for the computer room in the computing resource scheduling request, and generate a customized host pre-selection strategy based on the user's demand information for the host;

[0041] A computer room scheduling unit, configured to screen computer rooms according to the user-defined computer room pre-selection strategy and determine a target computer room to be called;

[0042] A host scheduling unit, configured to screen hosts in the target computer room according to the self-defined host pre-selection policy and determine a target host to be called;

[0043] The result generating unit is used to call the target host to provide computing services for the client.

[0044] A computer device comprising:

[0045] Memory for storing computer programs;

[0046] A processor is used to implement the steps of the above-mentioned edge computing resource scheduling method when executing the computer program.

[0047] A readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned edge computing resource scheduling method.

[0048] By applying the method provided in the embodiment of the present invention, corresponding custom computer room pre-selection strategies and custom host pre-selection strategies are generated according to the computing power demands of different clients, thereby determining the target computer room that meets the user's needs from the optional computer rooms according to the strategy, and selecting the target host that meets the user's needs from the target computer room, thereby scheduling the optimal computing power resources of the optimal node that meets the client's demands, adapting to the changing user business scenarios, and using the screened target host as the scheduling result to respond to user needs and improve user service quality.

[0049] Correspondingly, the embodiments of the present invention also provide edge computing resource scheduling devices, equipment and readable storage media corresponding to the above-mentioned edge computing resource scheduling method, which have the above-mentioned technical effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a flowchart of an implementation method for edge computing resource scheduling in an embodiment of the present invention;

[0052] Figure 2 This is a flowchart of another edge computing resource scheduling method according to an embodiment of the present invention;

[0053] Figure 3 This is a schematic diagram of the structure of an edge computing resource scheduling device in an embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram of an edge computing resource scheduling device according to an embodiment of the present invention;

[0055] Figure 5 Schematic diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The core of this invention is to provide an edge computing resource scheduling method that can meet the computing power demands of diverse business scenarios.

[0057] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0058] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for scheduling edge computing resources in an embodiment of the present invention, which includes the following steps:

[0059] S101: Receive a computing resource scheduling request initiated by a client;

[0060] The client initiates a computing power resource scheduling request, which indicates the current user's demand information for edge computing resources (i.e., computing power demand information), such as the computer room area, operator, computing power specifications, and ownership. The specific information types and dimensions are not limited and can be set according to the actual scheduling needs of the computer room and host. It can be roughly divided into two categories: computer room demand information and host demand information.

[0061] The computing power demand information indicates the user's customized personalized demand for edge computing resources. In this embodiment, it is possible to respond to and support the user's personalized demand for computing power resources.

[0062] Since computing power request information must contain evaluation items and evaluation values ​​that are clearly directed at resource scheduling, to simplify user operations and reduce operational complexity, the process of receiving computing power resource scheduling requests initiated by the client can be specifically performed according to the following steps:

[0063] (1) Receive user-specified application requirements sent by the client;

[0064] Specified application requirements can be scenario requirements, such as gaming scenarios, office scenarios, etc.; they can also be performance requirements, such as fast transmission speed, stable data transmission, etc. The application requirements can be configured according to user usage habits.

[0065] It should be noted that the application requirements specified by the user can be specified in a single dimension or in multiple dimensions, which is not limited in this embodiment.

[0066] (2) Determine the computing power demand information corresponding to the user's specified application requirements;

[0067] A corresponding computing power demand information item is set for each preset application requirement. After receiving the application requirement executed by the user, the computing power demand information corresponding to the user requirement can be directly obtained, avoiding the direct selection of attributes for edge computing, reducing the difficulty of user operation, and thus improving the user experience.

[0068] (3) Generate a scheduling request based on the computing power demand information as a computing power resource scheduling request.

[0069] The scheduling request is encapsulated according to the computing power demand information to obtain the computing power resource scheduling request.

[0070] It should be noted that this embodiment only takes the generation implementation method of the above-mentioned computing resource scheduling request as an example. Other implementation methods, such as receiving users' direct attribute scheduling of computing resources, can refer to the introduction of this embodiment and will not be repeated here.

[0071] S102: Generate a custom computer room pre-selection strategy based on the user's demand information for the computer room in the computing resource scheduling request, and generate a custom host pre-selection strategy based on the user's demand information for the host;

[0072] Computing resource scheduling requests primarily include two pieces of information: the user's requirements for computer rooms and the user's requirements for hosts. This embodiment generates customized computer room and host preselection strategies based on the user's diverse needs, thus satisfying these diverse user requirements.

[0073] The custom pre-selection strategy is a strategy generated based on the demands of the user in the client for the computer room resources. It can be a single-dimensional pre-selection strategy or a multi-dimensional pre-selection strategy. For example, a single-dimensional pre-selection strategy is: if the client specifies the resource partition as a, a resource partition pre-selection strategy will be generated to exclude computer rooms outside partition a; if the client specifies operator b, an operator pre-selection strategy will be generated to exclude computer rooms that do not have lines for the specified operator b. In this embodiment, only the two single-dimensional pre-selection strategies of resource partition and operator are used as examples for introduction. The settings of other single-dimensional pre-selection strategies or the settings of multi-dimensional pre-selection strategies can refer to the introduction of this embodiment and will not be repeated here.

[0074] Custom host preselection policies are also generated based on client requirements for host resources. These requirements might include client-specified resource specifications (CPU, GPU, memory, etc.) or specific requirements from the host provider. Custom host preselection policies can be cross-referenced with the description of custom preselection policies above and are not detailed here.

[0075] S103, screening the computer rooms according to the custom computer room pre-selection strategy to determine the target computer room to be called;

[0076] In order to improve resource scheduling efficiency and quickly select hosts that meet user needs, the resource scheduling in this embodiment is divided into two aspects: one is to determine the computer room that meets the user's usage needs, and the other is to select hosts that meet the user's usage needs in the determined computer room. Among them, the number of hosts determined is generally one. This embodiment only takes the example of selecting one host for each scheduling request as an introduction.

[0077] After determining the custom machine room pre-selection strategy, all available machine rooms are screened and checked one by one based on it, and the machine room that meets the custom machine room pre-selection strategy is determined as the target machine room. Due to the diversity of custom machine room pre-selection strategies generated by different users, the specific implementation process of machine room screening based on the custom machine room pre-selection strategy is not limited in this embodiment and can be set according to actual needs.

[0078] S104: Perform host screening in the target computer room according to the custom host pre-selection policy to determine the target host to be called;

[0079] After determining a unique target computer room, the target computer room may contain more than one host. Therefore, it is necessary to select a host suitable for the current user from among the multiple hosts in the target computer room as the target host. To achieve this, in this embodiment, host screening is performed in the target computer room according to a custom host pre-selection policy, and the unique host finally screened is selected as the target host.

[0080] Due to the diversity of customized host pre-selection policies generated by different users, the specific implementation process of performing host screening according to the customized host pre-selection policy is not limited in this embodiment and can be set according to actual needs.

[0081] S105: Call the target host to provide computing services to the client.

[0082] After determining the target host, the target host is used as the result of edge computing resource scheduling, and the target host is called to provide computing services to the client. The specific implementation process of calling the target host to provide computing services to the client can refer to the introduction of relevant technologies, which can include configuring the network of the target host to power on, and returning the information of the target host to the client, so that the client can determine the host to be called based on the information and make corresponding connections, etc.

[0083] The technical solution provided by the embodiment of the present invention generates corresponding customized computer room pre-selection strategies and customized host pre-selection strategies according to the computing power demands of different clients, thereby determining the target computer room that meets the user's needs from the optional computer rooms according to the strategy, and selecting the target host that meets the user's needs from the target computer room, thereby scheduling the optimal computing power resources of the optimal node that meets the client's demands, adapting to the changing user business scenarios, and using the screened target host as the scheduling result to respond to user needs and improve user service quality.

[0084] It should be noted that, based on the above-mentioned embodiments, the embodiments of the present invention also provide corresponding improved solutions. In the preferred / improved embodiments, the same steps or corresponding steps as those in the above-mentioned embodiments can be referenced to each other, and the corresponding beneficial effects can also be referenced to each other. These preferred / improved embodiments will not be described in detail one by one in this document.

[0085] In the above embodiment, there is no limitation on the specific implementation steps of screening the computer rooms and the hosts, and they can be set accordingly according to actual scheduling requirements.

[0086] In order to improve the retrieval efficiency, in addition to the customized computer room pre-selection strategy, the computer room scheduling strategy (a computer room screening strategy, according to which a computer room that meets the client's usage needs can be determined from several optional computer rooms) can also perform further preliminary selection.

[0087] Accordingly, the process of screening the computer rooms according to the customized computer room pre-selection strategy and determining the target computer room to be called can be performed in the following steps:

[0088] (1) Calling the preset general computer room pre-selection strategy to filter out available computer rooms from the optional computer rooms;

[0089] The general machine room preselection strategy is a system-provided strategy. As a general, basic screening strategy, it primarily filters out available machine rooms, thereby preventing interference from unavailable machine rooms during the selection process. For example, a general machine room preselection strategy can exclude machine rooms that are disabled, unreachable, or experiencing abnormal failures, thereby filtering out available machine rooms for subsequent selection. Of course, other default screening rules can also be set. This embodiment uses the above-mentioned screening of available machine rooms as an example.

[0090] (2) Call the custom computer room pre-selection strategy to filter out the computer room that meets the user's customized requirements from the available computer rooms as the target computer room to be called.

[0091] Through the general computer room pre-selection strategy and the customized computer room pre-selection strategy, available computer rooms that meet the conditions can be screened out to ensure the effectiveness of scheduling resources.

[0092] Furthermore, after calling the custom computer room pre-selection strategy to filter out computer rooms that meet the user's custom requirements from the available computer rooms, the following steps can be further performed:

[0093] (3) Determine whether the computer room that meets the user's customized requirements is unique;

[0094] (4) If yes, the computer room that meets the user's customized requirements is used as the target computer room to be called;

[0095] (5) If not, calculate the priority of the computer room call that meets the user's customized requirements;

[0096] (6) Determine the target computer room to be called according to the order of priority from high to low.

[0097] The call priority of each data center is calculated, and computing resources are requested from edge data centers in order of priority until the request is successful. Using general and customized policies, available data centers that meet the user's requirements are screened. The most suitable data center is then selected through the aforementioned optimization process, improving screening efficiency and quickly locating the optimal data center.

[0098] There is no limit on the specific evaluation rules for calling priority. The priority of the computer room can be evaluated based on the physical distance between the computer room and the client, the load of the computer room itself, and the number of equipment in the computer room. The corresponding rules can be set according to the actual needs of the computer room call.

[0099] Among them, a method for evaluating the priority of an equipment room is as follows: the equipment room call priority is evaluated based on the physical distance between the equipment room and the client and the load of the equipment room itself.

[0100] For example, a computer room priority algorithm formula is:

[0101] In the formula, D is the physical distance between the client and the computer room. m The effective distance threshold between the client and the computer room. If the distance exceeds this threshold, the computer room will not be able to provide computing power services to the client. w is the weighted value of the distance priority. L is the current load of the computer room, L m is the current load threshold of the computer room, L w The weighted value of the load priority.

[0102] The distance D between the client and the computer room can be calculated using the client's longitude and latitude and the computer room's longitude and latitude. In some scenarios where the client's longitude and latitude cannot be obtained, the client's IP address is obtained, matched to an internal IP database, and the corresponding operator and city are parsed. The longitude and latitude of the city center are roughly used as the client's location. This embodiment only uses the above two location determination methods as examples. The distance calculation process for other location determination methods can refer to the above description and will not be repeated here.

[0103] The load condition of the computer room can be calculated by periodically querying the current flow condition of the flow control device and the total bandwidth of the computer room. You can refer to the introduction of the relevant load determination method, which will not be repeated in this embodiment.

[0104] The physical distance between the client and the load of the computer room itself are negatively correlated with the priority of the computer room. By using physical distance and load as screening conditions, the computer room with a small current load and a short distance can be selected as the preferred computer room, thereby reducing transmission loss and avoiding excessive processing burden on the computer room.

[0105] It should be noted that, in this embodiment, only the above-mentioned priority determination method is used as an example for introduction. Other priority evaluation methods can refer to the above-mentioned introduction and will not be described in detail here.

[0106] It should be noted that the above describes a scheduling screening implementation method for a computer room, and the scheduling screening implementation method for a host can refer to the above scheduling screening implementation method for a computer room.

[0107] For example, in the target computer room, host screening is performed according to the custom host pre-selection policy, and the implementation process of determining the target host to be called can be:

[0108] (1) Calling the preset general host pre-selection strategy to filter out available hosts from the optional hosts in the target computer room;

[0109] The general host pre-selection policy is a system-provided policy, which mainly excludes disabled, non-idle, or faulty hosts.

[0110] (2) Call the custom computer room pre-selection strategy to filter out the computer room that meets the user's customized requirements from the available computer rooms as the target computer room to be called.

[0111] Furthermore, if the number of computer rooms that meet user needs determined by the custom computer room pre-selection strategy is not unique, it can be further generated based on the client's defined resource priority requirements. For example, for a certain scenario, high-configuration hosts can be prioritized, and low-configuration hosts can be selected as the optimal hosts.

[0112] like Figure 2 The figure shows a schematic diagram of the implementation process of performing three screenings (general screening, custom screening and priority screening) on ​​the computer room and the host respectively. The implementation of the method provided in the above embodiment can refer to Figure 2 , I will not go into details here.

[0113] The screening implementation process for the host can refer to the screening implementation method for the computer room, and the two can be compared with each other. The screening implementation method for the host in this embodiment will not be described in detail.

[0114] Furthermore, based on the above embodiment, in order to flexibly support and adapt to the changing resource demands of the client, this embodiment introduces a tag system. Before receiving the computing resource scheduling request initiated by the client, the following steps can be further performed:

[0115] (1) Setting attribute labels for each optional computer room according to the attribute information of the optional computer room;

[0116] The data center is labeled with multi-dimensional attributes based on its information, such as its location, operator line type, and agent.

[0117] (2) setting attribute tags for each optional host according to the attribute information of the optional host;

[0118] The host is labeled with multi-dimensional attributes based on its information, such as CPU, GPU, memory, and owner information.

[0119] Based on specific domains, we add different dimensional tags to data center and host resources. For example, we add region and operator tags to data centers, and hashrate specifications and ownership tags to hosts. When a client requests scheduling, the tag system converts the client's hashrate requirements into a series of custom tag selection policies, and then executes the scheduling. When a new resource requirement is added to a business scenario, simply add a tag matching the requirement.

[0120] Accordingly, the computer room is screened according to the custom computer room pre-selection strategy to determine the target computer room to be called, including: screening the computer room by comparing the attribute tags corresponding to each optional computer room according to the custom computer room pre-selection strategy to determine the target computer room to be called;

[0121] The client's data center requirements are parsed into a match of data center labels. After label filtering, a group of data centers that meet the requirements are obtained.

[0122] Performing host screening in the target computer room according to the custom host pre-selection policy to determine the target host to be called includes: performing host screening by comparing the attribute tags corresponding to the hosts in the target computer room according to the custom host pre-selection policy to determine the target host to be called.

[0123] The client's computing power requirements are parsed into host tag matching. After tag filtering, a group of hosts that meet the requirements are obtained.

[0124] In addition, priority filtering and general pre-selection filtering can also be implemented based on tags. For example, the client's computing power priority demand can be converted into a host tag priority match. For example, hosts with a memory tag of 16G are matched first, and hosts with a memory tag of 8 are matched second. For priority filtering and general pre-selection filtering, please refer to the implementation of custom filtering, which will not be repeated here.

[0125] It should be noted that no matter which step in the above embodiment is screened and no host or computer room that meets the corresponding conditions is found, the process can be terminated by returning no available resources. This embodiment does not limit the implementation method in this case and can be set accordingly according to actual usage needs.

[0126] Corresponding to the above method embodiment, an embodiment of the present invention also provides an edge computing resource scheduling device. The edge computing resource scheduling device described below and the edge computing resource scheduling method described above can be referenced to each other.

[0127] See also Figure 3 As shown, the device includes the following modules:

[0128] The request receiving unit 110 is mainly used to receive computing resource scheduling requests initiated by the client;

[0129] The strategy generation unit 120 is mainly used to generate a customized computer room pre-selection strategy based on the user's demand information for the computer room in the computing resource scheduling request, and to generate a customized host pre-selection strategy based on the user's demand information for the host;

[0130] The computer room scheduling unit 130 is mainly used to screen computer rooms according to the customized computer room pre-selection strategy and determine the target computer room to be called;

[0131] The host scheduling unit 140 is mainly used to screen hosts in the target computer room according to the custom host pre-selection strategy and determine the target host to be called;

[0132] The result generating unit 150 is mainly used to call the target host to provide computing services for the client.

[0133] In this embodiment, the scheduling of computing resources is divided into three layers: application layer, scheduling layer, and resource layer. Figure 4 shown.

[0134] The application layer refers to client applications in different scenarios. The request receiving unit 110 receives computing resource scheduling requests initiated by the client on different applications at the application layer.

[0135] The scheduling layer is the core middle layer of the entire system. Three modules, including the policy generation unit 120, the computer room scheduling unit 130 and the host scheduling unit 140, run in the scheduling layer and are responsible for receiving scheduling requests from the application layer, generating scheduling policies and executing scheduling tasks.

[0136] The resource layer is the computing resource pool for each edge node, responsible for scheduling edge computing power, managing resources within the computer room (computer room hosts), and maintaining the entire lifecycle of computing resources. The result generation unit 150 is built on the resource layer to enable direct calls to target resources (target hosts) to meet user needs.

[0137] Corresponding to the above method embodiment, an embodiment of the present invention further provides a computer device. The computer device described below and the edge computing resource scheduling method described above can refer to each other.

[0138] The computer equipment includes:

[0139] Memory for storing computer programs;

[0140] A processor is used to implement the steps of the edge computing resource scheduling method of the above method embodiment when executing a computer program.

[0141] For details, please refer to Figure 5 , is a schematic diagram of the specific structure of a computer device provided in this embodiment. The computer device may vary greatly due to different configurations or performances, and may include one or more processors (central processing units, CPU) 322 (for example, one or more processors) and a memory 332, and the memory 332 stores one or more computer applications 342 or data 344. Among them, the memory 332 can be a temporary storage or a permanent storage. The program stored in the memory 332 may include one or more modules (not shown in the figure), each of which may include a series of instruction operations in the data processing device. Furthermore, the central processing unit 322 can be configured to communicate with the memory 332 to execute a series of instruction operations in the memory 332 on the computer device 301.

[0142] The computer device 301 may also include one or more power supplies 326 , one or more wired or wireless network interfaces 350 , one or more input and output interfaces 358 , and / or one or more operating systems 341 .

[0143] The steps in the edge computing resource scheduling method described above can be implemented by the structure of a computer device.

[0144] Corresponding to the above method embodiment, an embodiment of the present invention further provides a readable storage medium. The readable storage medium described below and the edge computing resource scheduling method described above can refer to each other.

[0145] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the edge computing resource scheduling method of the above-mentioned method embodiment.

[0146] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0147] Those skilled in the art may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Claims

1. A method for scheduling edge computing resources, characterized in that: include: Receive computing resource scheduling requests initiated by clients; Generate a custom computer room pre-selection strategy based on the user's demand information for the computer room in the computing resource scheduling request, and generate a custom host pre-selection strategy based on the user's demand information for the host; Calling the preset general computer room pre-selection strategy to filter out available computer rooms from the optional computer rooms; Calling the custom computer room pre-selection strategy to filter out a computer room that meets the user's custom requirements from the available computer rooms, and determining whether the computer room that meets the user's custom requirements is unique; If yes, the computer room that meets the user's customized requirements is used as the target computer room to be called; If not, evaluate the priority of the computer room call based on the physical distance between the client and the load of the computer room itself; Determine the target computer room to be called according to the order of priority from high to low; In the target computer room, host screening is performed according to the custom host pre-selection strategy to determine the target host to be called; The target host is called to provide computing services for the client.

2. The edge computing resource scheduling method according to claim 1, characterized in that: The method for determining the physical location distance includes: Determine whether the longitude and latitude information of the client can be obtained; If available, the physical location distance between the computer room and the client is calculated based on the latitude and longitude information of the client and the latitude and longitude information of each computer room; If unavailable, determine the IP address of the client; Resolve the operating city corresponding to the IP address; The central longitude and latitude of the operating city are used as the longitude and latitude information of the client, and the step of calculating the physical location distance between the computer room and the client based on the longitude and latitude information of the client and the longitude and latitude information of each computer room is performed.

3. The edge computing resource scheduling method according to claim 1, characterized in that: The receiving a computing resource scheduling request initiated by a client includes: Receive user-specified application requirements sent by the client; Determine the computing power demand information corresponding to the user-specified application requirements; A scheduling request is generated according to the computing power demand information as the computing power resource scheduling request.

4. The edge computing resource scheduling method according to any one of claims 1 to 3, characterized in that: Before receiving the computing resource scheduling request initiated by the client, the method further includes: According to the attribute information of the optional computer room, an attribute label is set for each of the optional computer rooms; According to the attribute information of the optional host, an attribute tag is set for each optional host; Accordingly, screening the computer rooms according to the self-defined computer room pre-selection strategy to determine the target computer room to be called includes: screening the computer rooms according to the self-defined computer room pre-selection strategy and comparing the attribute tags corresponding to each optional computer room to determine the target computer room to be called; In the target computer room, host screening is performed according to the custom host pre-selection strategy to determine the target host to be called, including: according to the custom host pre-selection strategy, host screening is performed by comparing the attribute tags corresponding to each host in the target computer room to determine the target host to be called.

5. An edge computing resource scheduling device, characterized in that: include: A request receiving unit, used to receive a computing resource scheduling request initiated by a client; A strategy generating unit, configured to generate a custom computer room pre-selection strategy according to the user's demand information for the computer room in the computing resource scheduling request, and to generate a custom host pre-selection strategy according to the user's demand information for the host; The computer room dispatching unit is used to: Calling the preset general computer room pre-selection strategy to filter out available computer rooms from the optional computer rooms; Calling the custom computer room pre-selection strategy to filter out a computer room that meets the user's custom requirements from the available computer rooms, and determining whether the computer room that meets the user's custom requirements is unique; If yes, the computer room that meets the user's customized requirements is used as the target computer room to be called; If not, evaluate the priority of the computer room call based on the physical distance between the client and the load of the computer room itself; Determine the target computer room to be called according to the order of priority from high to low; A host scheduling unit, used to screen hosts in the target computer room according to the self-defined host pre-selection strategy, and determine the target host to be called; The result generating unit is used to call the target host to provide computing services for the client.

6. A computer device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the edge computing resource scheduling method as described in any one of claims 1 to 4 when executing the computer program.

7. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the edge computing resource scheduling method according to any one of claims 1 to 4 are implemented.

Images