Edge computing-based resource processing method and apparatus

Abstract

The present disclosure relates to the technical field of cloud computing. Disclosed are an edge computing-based resource processing method and an apparatus. The method comprises: acquiring a resource processing request received by a target resource processing interface, the target resource processing interface being any one of multiple different types of resource processing interfaces, and the resource processing request comprising key information and resource description information; using the key information to search a machine room library for a corresponding machine room; and, on the basis of processing logic of the target resource processing interface and the resource description information, executing a resource processing operation on the machine room.

Description

A resource processing method and device based on edge computing

[0001] Cross-reference to Related Applications

[0002] The present application claims priority to the Chinese patent application No. 202410865562.6, filed on June 28, 2024, and entitled "A resource processing method and device based on edge computing", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of cloud computing, and in particular to a resource processing method and device based on edge computing. BACKGROUND

[0004] Edge computing is a new computing mode that processes and analyzes data on the data generation side at the edge of the network. Its advantage is that it can improve the overall availability and scalability of the system by pushing data to the edge of the Internet to reduce latency, save bandwidth and related costs. In particular, in scenarios that require fast response, processing of large amounts of data, or have special requirements for privacy and security, such as industrial automation, intelligent driving, remote medical care and the Internet of Things, edge computing has significant advantages. SUMMARY

[0005] Therefore, the embodiments of the present disclosure provide a resource processing method and device based on edge computing.

[0006] In a first aspect, the embodiments of the present disclosure provide a resource processing method based on edge computing, which is applied to an edge cloud computing system, and the method comprises:

[0007] Obtaining a resource processing request received by a target resource processing interface, wherein the target resource processing interface is any one of a plurality of different types of resource processing interfaces, and the resource processing request comprises key information and resource description information;

[0008] Finding a corresponding machine room from a machine room library by using the key information;

[0009] Performing a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information.

[0010] In a second aspect, the embodiments of the present disclosure provide a resource scheduling device based on edge computing, which comprises:

[0011] The acquisition module is configured to acquire a resource processing request received by a target resource processing interface, wherein the target resource processing interface is any one of a plurality of different types of resource processing interfaces, and the resource processing request comprises key information and resource description information.

[0012] The searching module is configured to search for a corresponding machine room from a machine room library by using the key information.

[0013] The execution module is configured to perform a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information.

[0014] In a third aspect, the embodiments of the present disclosure provide a computer device, including a memory and a processor, which are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method in the first aspect or any of the corresponding embodiments.

[0015] In a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the method in the first aspect or any of the corresponding embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the specific embodiments or the related art of the present disclosure, the drawings needed in the specific embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present disclosure, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0017] FIG. 1 is a flow diagram of a resource processing method based on edge computing according to some embodiments of the present disclosure;

[0018] FIG. 2 is a flow diagram of a resource processing method based on edge computing according to some embodiments of the present disclosure;

[0019] FIG. 3 is a flow diagram of a resource processing method based on edge computing according to some embodiments of the present disclosure;

[0020] FIG. 4 is a schematic diagram of capacity expansion of an elastic scaling controller according to some embodiments of the present disclosure;

[0021] FIG. 5 is a schematic diagram of disaster recovery of an elastic scaling controller according to some embodiments of the present disclosure;

[0022] FIG. 6 is a structural block diagram of a resource processing apparatus based on edge computing according to an embodiment of the present disclosure;

[0023] FIG. 7 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0025] With the increase in the number of edge computer rooms and the increase in the difference in the size of individual computer rooms, resource management and scheduling become more and more complex. In the current edge computing scenario, due to the large number of computer rooms and the large difference in the size of individual computer rooms, the workload of managing the number of instances of resources one by one is very large.

[0026] According to the embodiments of the present disclosure, a resource processing method and device based on edge computing are provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a group of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] In the present embodiment, a resource processing method based on edge computing is provided, which can be used in the above mobile terminal, such as mobile phone, tablet computer, etc. (the execution subject is described in combination with the actual situation), and FIG. 1 is a flowchart of a resource processing method based on edge computing according to an embodiment of the present disclosure. As shown in FIG. 1, the flow includes the following steps:

[0028] Step S11, acquiring a resource processing request received by a target resource processing interface, wherein the target resource processing interface is any one of a plurality of different types of resource processing interfaces, and the resource processing request includes key information and resource description information.

[0029] In the present embodiment of the present disclosure, the edge cloud computing system includes a plurality of nodes, each node having certain computing and storage resources. The edge cloud computing system is deployed with a scheduler, which is a component responsible for effective allocation and scheduling of these resources. Specifically, the scheduler provides the following three interfaces:

[0030] Resource planning interface: This interface uses algorithms and strategies to plan the resource usage in each computer room and provides a reasonable resource allocation scheme. For example, it can develop a reasonable resource planning scheme according to the hardware devices, network connections, load conditions, and other factors in the computer room to ensure the performance and stability of the system.

[0031] Resource application interface: This interface allows users to submit resource application requests at the granularity of machine rooms. Users can apply for a certain amount of computing and storage resources according to their own needs and specify the machine room to which the resources are applied. The scheduler allocates and schedules resources through the multi-machine room resource planning interface to meet the needs of users.

[0032] Resource release interface: This interface allows users to release the resources they have applied for. Users can specify the machine room to be released and the type and quantity of resources to be released. In this way, the system can timely recover these resources to better provide resource services for other users.

[0033] In the embodiments of the present disclosure, when the target resource processing interface receives a resource processing request, it first determines the type of the target resource processing interface, which can be a resource planning interface, a resource application interface, or a resource release interface. Then it determines what type of resource processing request to execute. The resource processing request contains two types of information: key information and resource description information. The key information can be regional information or machine room information. Regional information refers to a geographical or logical region in an edge cloud computing system, which can be used to describe the distribution of resources, network connectivity, and the like. In the scheduler, regional information can help the system determine the scope and limitations of resource allocation. For example, some regions may have more resources available for allocation, while other regions may require special consideration due to poor network connectivity or other factors. Machine room information refers to a physical or logical machine room in an edge cloud computing system, which is the basic unit of resource scheduling and management. In the scheduler, machine room information can be used to determine the actual location and distribution of resources, as well as the connection method and bandwidth between machine rooms. Through machine room information, the system can more accurately plan, apply, and release resources. For example, a user may wish to limit resource application to a specific machine room or release resources in a certain machine room. Resource description information is related information about the resource to be processed, which can include the type, size, format, location, and the like of the resource.

[0034] Step S12: Use the key information to find the corresponding machine room from the machine room library.

[0035] In the embodiments of the present disclosure, when the target resource processing interface is a resource planning interface, the key information carried by the resource processing request received by the interface is regional information. When the target resource processing interface is a resource application interface, the key information carried by the resource processing request received by the interface is machine room information. When the target resource processing interface is a resource release interface, the key information carried by the resource processing request received by the interface is machine room information.

[0036] In the embodiments of the present disclosure, the system first needs to obtain the machine room information stored in the machine room library. These information usually includes the name of the machine room, the geographical location, the region to which it belongs, the available resource situation (such as computing resources, storage resources, etc.), the network connection situation, etc. Then, according to the key information (region information or machine room information) provided by the user, the system needs to determine the query condition. If the user provides the region information, the system needs to match all the machine rooms in the region; if the user provides the machine room information, the system needs to directly match the machine room. According to the determined query condition, the system performs a query operation in the machine room library. If it is queried according to the region information, the system traverses all the machine rooms in the machine room library and filters out the machine rooms whose regions match the region information provided by the user; if it is queried according to the machine room information, the system directly matches the machine room whose name matches the machine room information provided by the user in the machine room library.

[0037] In step S13, a resource processing operation is performed on the machine room based on the processing logic of the target resource processing interface and the resource description information.

[0038] In the embodiments of the present disclosure, performing a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information includes: in the case where the target resource processing interface is a resource planning interface, determining a screening condition and a combination condition based on the processing logic of the resource planning interface; combining the machine rooms according to the combination condition to obtain a plurality of machine room combinations; obtaining a candidate machine room combination that satisfies the screening condition from the machine room combinations; evaluating the candidate machine room combination according to a preset evaluation strategy in the resource description information to obtain an index value corresponding to the candidate machine room, and taking the candidate machine room combination with the highest index value as a target machine room combination; obtaining a first resource situation of each target machine room in the target machine room combination; generating resource planning information based on the first resource situation, and sending the resource planning information to a requester corresponding to the resource processing request.

[0039] Specifically, in the case where the target resource processing interface is a resource planning interface, the screening condition and the combination condition are determined based on the processing logic of the resource planning interface. The screening condition can be the maximum instance number of a single machine room, the minimum instance number, etc. The maximum instance number of a single machine room refers to the maximum number of instances that a machine room can accommodate. It is necessary to ensure that the number of instances of each machine room in the selected machine room combination does not exceed its maximum instance number limit. The minimum instance number refers to the minimum number of instances required by a machine room, which ensures that the number of instances of each machine room in the selected machine room combination does not fall below its minimum instance number limit. The combination condition is used to select and combine machine rooms that meet the condition from the inventory. It can include factors such as the geographical location, network connection, hardware configuration, etc. of the machine room. For example, an algorithm can be defined to evaluate the availability and performance of each machine room, and the machine rooms are selected and combined according to these factors. According to the pre-defined combination condition, the machine rooms that meet the condition are selected from the machine room inventory and combined into a plurality of machine room combinations.

[0040] Then the candidate data center combinations that meet the above screening conditions (maximum number of instances in a single data center, minimum number of instances) are screened out from the data center combination. The preset evaluation strategy in the resource description information is obtained, and the preset evaluation strategy includes performance indicators, reliability, cost, etc. Each candidate data center combination is evaluated to obtain the index value corresponding to the candidate data center.

[0041] For example: data center combination X evaluation: performance indicator calculation: bandwidth weight is 0.6, delay weight is 0.4. By multiplying the bandwidth value 800Mbps by the bandwidth weight 0.6 and the delay value 5ms by the delay weight 0.4, the weighted values of each item are 480 and 2 respectively. Then add them up and divide by the weight sum (0.6+0.4=1), the calculation result of the performance indicator is 482Mbps.

[0042] Data center Y evaluation: performance indicator calculation: bandwidth weight is 0.6, delay weight is 0.4. By multiplying the bandwidth value 1000Mbps by the bandwidth weight 0.6 and the delay value 3ms by the delay weight 0.4, the weighted values of each item are 600 and 1.2 respectively. Then add them up and divide by the weight sum (0.6+0.4=1), the calculation result of the performance indicator is 601.2Mbps.

[0043] Finally, according to the evaluation result, the candidate data center combination with the highest index value is selected as the target data center combination. The first resource situation of each target data center in the selected target data center combination is obtained, including instance number, hardware configuration, network connection and other information. Based on the first resource situation of each target data center in the target data center combination, resource planning information is generated and sent to the requestor corresponding to the resource processing request to meet the resource demand of the requestor.

[0044] It should be noted that through the resource planning interface, it can intelligently plan which data centers to deploy and how many instances to deploy in each data center based on different regions and resource description information. This greatly improves resource utilization and management efficiency, while reducing the complexity and error rate of manual operation.

[0045] The embodiments of the present disclosure utilize key information to find the corresponding data center from the data center library. The data center that needs to process the resource can be accurately found according to the key information, avoiding misoperation and waste of resources. Then, based on the processing logic of the target resource processing interface and the resource description information, the resource processing operation is performed on the data center. According to the specific characteristics and needs of the resource, the appropriate processing method is selected, and the efficiency of resource processing is improved.

[0046] FIG. 2 is a flowchart of a resource processing method based on edge computing according to an embodiment of the present disclosure, as shown in FIG. 2, the flow includes the following steps:

[0047] Step S21, obtaining a resource processing request received by a target resource processing interface, wherein the target resource processing interface is any one of a plurality of different types of resource processing interfaces, and the resource processing request includes key information and resource description information. For details, see step S11 in the above embodiment, which will not be described in detail here.

[0048] Step S22, searching for a corresponding machine room from the machine room library using the key information. For details, see step S12 in the above embodiment, which will not be described in detail here.

[0049] Step S23, performing a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information.

[0050] In the embodiments of the present disclosure, performing a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information includes the following steps A1-A3:

[0051] Step A1, in the case where the target resource processing interface is a resource application interface, determining a second resource condition in the resource pool based on the processing logic of the resource application interface.

[0052] Specifically, determining the current resource condition of the resource pool is mainly achieved by resource pool analysis. Resource pool analysis refers to monitoring computing, storage and network resources in multiple dimensions such as region, resource pool, available partition and host group, and evaluating the capacity and load condition of the resource pool in combination with key performance indicators. Specifically, the resources need to be abstracted and defined first, which includes computing resources, storage resources and network resources, etc. Then, these resources are abstracted into an extensible and dynamic resource pool, and when a resource application is proposed, the corresponding resources are provided from the resource pool according to the demand.

[0053] Step A2, checking whether the second resource condition meets the resource description information to obtain a checking result.

[0054] Specifically, it is checked whether the corresponding type of resource in the resource pool is sufficient to meet the resource demand in the resource description information. Specifically, it includes checking whether the quantity, attributes and other constraint conditions of the resource meet the demand.

[0055] Step A3, performing a resource processing operation on the machine room according to the checking result.

[0056] Specifically, if the resources in the resource pool are sufficient to meet the demand, the system can perform resource allocation and update the state and quantity of the corresponding resources in the resource pool. If the resources are insufficient or cannot meet the application requirements, the application needs to be rejected, and the corresponding error information is returned. In addition, after processing the resource application, the system needs to update the state information of the resources in the resource pool in a timely manner, including the number of allocated resources, the number of available resources, etc.

[0057] According to the check result, the resource processing operation is performed on the machine room, including: if the check result is that the second resource condition does not meet the resource description information, a first feedback result is sent to the requestor corresponding to the resource processing request, the first feedback result including resource application failure and failure reason; or, if the check result is that the second resource condition meets the resource description information, a second feedback result is sent to the requestor corresponding to the resource processing request, the second feedback result including resource application success and resource allocation information.

[0058] In the case that the check result is that the resource condition does not meet the resource description information, the system first needs to determine the specific reason for the resource application failure, for example: resource shortage, resource attribute mismatch, resource state exception. Then, the system generates feedback information, which explicitly indicates that the resource application fails and details the reason for the failure. This feedback information can include error code, error description and possible solution suggestions. Next, the system sends the generated first feedback result to the requestor of the resource processing request.

[0059] In the case that the check result is that the resource condition meets the resource description information, a second feedback result is sent to the requestor corresponding to the resource processing request, the second feedback result including resource application success and resource allocation information. The specific processing logic is as follows: generate feedback information: the system generates feedback information, confirming that the resource application is successful, and providing related information of resource allocation, including the type, quantity, usage instructions, etc. of the allocated resources. Send the feedback result: send the generated second feedback result to the requestor of the resource processing request to ensure that it learns the message and related information of the successful resource application in a timely manner.

[0060] The embodiments of the present disclosure determine the second resource condition in the resource pool based on the processing logic of the resource application interface, so that the system can realize dynamic management of resources. Thus, the demand for resources of different requests can be better met. At the same time, by checking whether the resource condition meets the resource description information, the resources in the resource pool can be effectively utilized. The situation of idle resources or insufficient resources is avoided, thereby improving the utilization rate of resources. According to the check result, the resource processing operation is performed on the machine room, so that the dynamic allocation and adjustment of resources can be performed according to the actual demand. In this way, it can be ensured that the resources are reasonably allocated to different tasks or requests, thereby optimizing the utilization and allocation of resources.

[0061] FIG. 3 is a flow chart of a resource processing method based on edge computing according to an embodiment of the present disclosure. As shown in FIG. 3, the flow includes the following steps:

[0062] In step S31, a resource processing request received by a target resource processing interface is acquired, where the target resource processing interface is any one of a plurality of different types of resource processing interfaces, and the resource processing request includes key information and resource description information. For details, refer to step S11 in the above embodiments, which will not be described here in detail.

[0063] In step S32, the key information is used to find a corresponding machine room from a machine room library. For details, refer to step S12 in the above embodiments, which will not be described here in detail.

[0064] In step S33, a resource processing operation is performed on the machine room based on the processing logic of the target resource processing interface and the resource description information.

[0065] In the embodiment of the present disclosure, performing a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information includes the following steps B1-B3:

[0066] In step B1, in the case where the target resource processing interface is a resource release interface, the processing logic of the resource release interface is used to determine the to-be-released resource corresponding to the resource description information.

[0067] In step B2, it is detected whether the to-be-released resource exists in the machine room.

[0068] In step B3, in the case where the to-be-released resource exists in the machine room, a release operation is performed on the to-be-released resource, a resource release result is obtained, and the resource release result is sent to a requester corresponding to the resource processing request.

[0069] First, it is determined which resources need to be released based on the resource description information. The resources in the machine room are detected to confirm whether there are resources that need to be released. If there are to-be-released resources in the machine room, a release operation needs to be performed on these resources. After the release operation is performed, the result of the release operation is obtained. It can be success, failure or other related state information. Finally, the result of the resource release is fed back to the requester of the resource processing request. This can be completed through a corresponding communication mode, such as a network request or message passing.

[0070] It should be noted that when a user no longer needs some resources, the resources can be released back through the interface. In particular, when an IP is released, a specific IP can also be specified, so that the management of resources is more precise and accurate.

[0071] The method provided by the embodiments of the present disclosure can automatically determine which resources need to be released based on the processing logic of the resource release interface, without manual intervention, thereby improving the automation and efficiency of the system. At the same time, timely release of unnecessary resources can effectively reduce resource waste, especially in a cloud computing environment, avoiding long-term occupation of resources without use, saving costs. In addition, releasing unnecessary resources can enable other tasks or requests to obtain resources more quickly, improve resource utilization, and improve the overall performance of the system.

[0072] In the embodiments of the present disclosure, the method further includes steps C1-C4:

[0073] Step C1, obtaining instance load data of each region in the edge cloud computing system.

[0074] Specifically, the elastic scaling controller first communicates with the edge cloud computing system to obtain instance load data of each region. These data may include CPU usage, memory consumption, network traffic and other indicators, which are used to evaluate the load of the instance.

[0075] Step C2, determining a target instance whose load data meets the expansion condition, and querying a first region where the target instance corresponds to an original machine room.

[0076] Specifically, the elastic scaling controller will determine the target instance that needs to be expanded according to the pre-set expansion condition, such as the load of the instance in a certain region exceeding a certain threshold. Once the target instance is determined, the elastic scaling controller will query the first region where the target instance corresponds to the original machine room. This may be to ensure that the expanded instance is close to the original instance in physical location to reduce latency and improve performance.

[0077] Step C3, detecting whether the available resources of the first region support performing the expansion operation.

[0078] Specifically, the elastic scaling controller will perform resource detection on the first region to confirm whether the region has sufficient available resources to perform the expansion operation. This may involve checking available computing resources (CPU, memory, etc.), network resources, and storage resources, etc.

[0079] Step C4, in the case that the available resources support performing the expansion operation, obtaining instance planning information, and performing the expansion operation on the first region according to the instance planning information.

[0080] Specifically, if the available resources of the first region meet the requirements of the expansion operation, the elastic scaling controller will obtain instance planning information. This can include the number of instances that need to be added, instance types, configuration information, etc. Finally, it will perform the expansion operation on the first region according to these planning information, ensuring that the system can respond to load increases in a timely manner, while minimizing resource waste and costs.

[0081] In the embodiments of the present disclosure, the method further comprises: generating alarm information in the case that the available resources do not support the execution of the expansion operation; obtaining resource adjustment information based on the feedback of the alarm information; and adjusting the available resources of the first region according to the resource adjustment information until the available resources of the first region support the execution of the expansion operation.

[0082] It should be noted that, as shown in FIG. 4, the elastic scaling controller will periodically check instance load data, and if the load data meets the expansion condition, it will trigger the expansion operation. The expansion condition can be, for example, CPU usage, memory usage, etc. Next, the elastic scaling controller will call the resource planning interface to plan the distribution of new instances. This process will take into account the resource situation in the same region of the original computer room, such as available racks, IP addresses, network planning, etc. If the resources in this region are insufficient, an alarm will be triggered or a notification will be sent. According to the planning result returned by the resource planning interface, the elastic scaling controller will call the instance deployment API to expand according to the planned computer room and instance number. This process includes creating new instances, allocating IP addresses, binding networks, installing applications, etc.

[0083] The embodiments of the present disclosure periodically check instance load data through the elastic scaling controller, and automatically expand or shrink according to the load situation, which can improve the availability and performance of the system. If the load increases, it can respond faster and avoid system overload or service interruption due to insufficient resources. By dynamically adjusting resources according to business needs and actual load conditions, computing resources can be better managed and utilized, thereby improving resource utilization efficiency and reducing resource waste. Ultimately, automatic elastic scaling of services is achieved, making infrastructure management more flexible and automated.

[0084] In the embodiments of the present disclosure, the method further comprises steps D1-D4:

[0085] Step D1, obtaining an abnormal instance list in the edge cloud computing system, wherein the abnormal instance list includes abnormal instances of each computer room.

[0086] Specifically, the elastic scaling controller can obtain an abnormal instance list in the edge cloud computing system. The list includes abnormal instances of each computer room, which can have problems such as failure, high load, insufficient resources, etc.

[0087] Step D2: Obtain the abnormal time corresponding to each abnormal instance, and take the abnormal instance whose abnormal time exceeds the preset time as the target abnormal instance.

[0088] Specifically, the elastic scaling controller obtains the abnormal time corresponding to each abnormal instance, and takes the abnormal instance whose abnormal time exceeds the preset time as the target abnormal instance. In this way, only instances that have been abnormal for a long time are processed, reducing false positives and interference.

[0089] Step D3: Detect the available resources of the original machine room corresponding to the target abnormal instance.

[0090] Specifically, the elastic scaling controller detects the available resources of the original machine room corresponding to the target abnormal instance to confirm whether the machine room has enough resources to handle the abnormal situation.

[0091] Step D4: If the available resources of the original machine room do not meet the preset conditions, add a new machine room in the second area, wherein the second area is the area where the original machine room is located.

[0092] Specifically, if the available resources of the original machine room do not meet the preset conditions, the elastic scaling controller will add a second area in the area where the original machine room is located. Ensure that the newly added machine room is close to the original machine room in physical location to reduce latency and improve performance.

[0093] Step D5: Perform expansion operation on the newly added machine room, and perform shrink operation on the target abnormal instance in the original machine room.

[0094] Specifically, if the newly added machine room is available, the elastic scaling controller will perform an expansion operation in the second area to ensure that the system has enough computing resources to handle abnormal situations. At the same time, it will perform a shrink operation on the target abnormal instance in the original machine room to avoid resource waste and cost increase. In short, in this way, the elastic scaling controller can flexibly adapt to abnormal situations in edge cloud computing systems and maximize the use of system resources.

[0095] It should be noted that, as shown in FIG. 5, the elastic scaling controller periodically acquires the list of abnormal instances. If the instance abnormal duration exceeds the threshold, the elastic scaling controller will start the disaster recovery process. First, the elastic scaling controller calls the resource planning interface to check whether there are available resources in the original machine room where the target abnormal instance is located. If there are available resources in the original machine room, the disaster recovery process will be suspended and no operation will be performed. However, if the original machine room is insufficient in resources, the disaster recovery process will continue. Next, the elastic scaling controller plans a new machine room in the same area as the original machine room and expands the new machine room. For example, x instances are planned in the same area by the scheduler, and the scheduler returns the planning result, in which b machine room y instances, c machine room z instances. This step aims to ensure that the new machine room is close to the original machine room in geographical location, so as to reduce data transmission delay and improve service reliability. Finally, according to the planning result, the elastic scaling controller calls the instance deployment API to expand the newly planned machine room and shrink the abnormal instances in the original machine room. In this way, the high availability of the business can be ensured, and the resources can be effectively utilized.

[0096] The embodiments of the present disclosure can reduce manual intervention, speed up fault recovery time, and improve the availability and reliability of the system by automatically detecting abnormal instances and starting the disaster recovery process. Before triggering disaster recovery, it is checked whether there are available resources in the original machine room, so that unnecessary disaster recovery actions can be avoided, and resources and costs can be saved. By planning a new machine room in the same area, the geographical distribution of resources can be made more reasonable, which helps to improve the access speed of the service. According to the resource planning result, the new machine room is expanded and the abnormal instances in the original machine room are shrunk, so that the resource allocation can be flexibly adjusted to ensure the stability of the service.

[0097] In addition, the system can better cope with sudden traffic changes and faults, and improve the flexibility and adaptability of the system. When a fault occurs, resource switching and fault recovery can be quickly performed to ensure the continuity of the business and the integrity of the data. Through integrated API calling and automatic processes, the complexity of disaster recovery and resource management is simplified, and the operation is more convenient.

[0098] In the embodiments, a resource scheduling device based on edge computing is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and details are not repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and contemplated.

[0099] The embodiments provide a resource scheduling device based on edge computing, as shown in FIG. 6, which includes:

[0100] The acquisition module 61 is configured to acquire a resource processing request received by a target resource processing interface, wherein the target resource processing interface is any one of a plurality of different types of resource processing interfaces, and the resource processing request comprises key information and resource description information;

[0101] The searching module 62 is configured to search for a corresponding machine room from the machine room library by using the key information.

[0102] The execution module 63 is configured to perform a resource processing operation on the machine room based on the processing logic of the target resource processing interface and the resource description information.

[0103] In the embodiments of the present disclosure, the execution module 63 is configured to, in a case where the target resource processing interface is a resource planning interface, determine a screening condition and a combination condition based on the processing logic of the resource planning interface; combine the machine rooms according to the combination condition to obtain a plurality of machine room combinations; obtain a candidate machine room combination that meets the screening condition from the machine room combinations; evaluate the candidate machine room combination according to a preset evaluation strategy in the resource description information, to obtain an index value corresponding to the candidate machine room, and take the candidate machine room combination with the highest index value as a target machine room combination; obtain a first resource condition of each target machine room in the target machine room combination; generate resource planning information based on the first resource condition, and send the resource planning information to a requester corresponding to the resource processing request.

[0104] In the embodiments of the present disclosure, the execution module 63 is configured to, in a case where the target resource processing interface is a resource planning interface, determine a second resource condition in a resource pool based on the processing logic of the resource planning interface; check whether the second resource condition meets the resource description information, to obtain a checking result; perform a resource processing operation on the machine room according to the checking result; wherein performing the resource processing operation on the machine room according to the checking result comprises: in a case where the checking result is that the second resource condition does not meet the resource description information, sending a first feedback result to the requester corresponding to the resource processing request, the first feedback result comprising resource application failure and a failure reason; or, in a case where the checking result is that the second resource condition meets the resource description information, sending a second feedback result to the requester corresponding to the resource processing request, the second feedback result comprising resource application success and resource allocation information.

[0105] In the embodiments of the present disclosure, the execution module 63 is configured to, in a case where the target resource processing interface is a resource planning interface, determine a second resource condition in a resource pool based on the processing logic of the resource planning interface; check whether the second resource condition meets the resource description information, to obtain a checking result; perform a resource processing operation on the machine room according to the checking result; wherein performing the resource processing operation on the machine room according to the checking result comprises: in a case where the checking result is that the second resource condition does not meet the resource description information, sending a first feedback result to the requester corresponding to the resource processing request, the first feedback result comprising resource application failure and a failure reason; or, in a case where the checking result is that the second resource condition meets the resource description information, sending a second feedback result to the requester corresponding to the resource processing request, the second feedback result comprising resource application success and resource allocation information.

[0106] In the embodiment of the present disclosure, the resource scheduling device based on edge computing comprises: an expansion module configured to acquire instance load data of each region in an edge cloud computing system; determine a target instance whose load data meets an expansion condition, and query a first region where an original machine room corresponding to the target instance is located; detect whether available resources of the first region support performing an expansion operation; in the case that the available resources support performing the expansion operation, acquire instance planning information, and perform the expansion operation on the first region according to the instance planning information.

[0107] In the embodiment of the present disclosure, the resource scheduling device based on edge computing further comprises: a generation module configured to, in the case that the available resources do not support performing the expansion operation, generate alarm information; acquire resource adjustment information fed back based on the alarm information; and adjust the available resources of the first region according to the resource adjustment information until the available resources of the first region support performing the expansion operation.

[0108] In the embodiment of the present disclosure, the resource scheduling device based on edge computing further comprises: a processing module configured to acquire an abnormal instance list in the edge cloud computing system, wherein the abnormal instance list comprises abnormal instances of each machine room; acquire abnormal time corresponding to each abnormal instance, and take an abnormal instance whose abnormal time exceeds a preset time as a target abnormal instance; detect available resources of an original machine room corresponding to the target abnormal instance; in the case that the available resources of the original machine room do not meet a preset condition, add a new machine room in a second region, wherein the second region is a region where the original machine room is located; perform an expansion operation on the new machine room, and perform a contraction operation on the target abnormal instance in the original machine room.

[0109] Referring to FIG. 7, FIG. 7 is a structural schematic diagram of a computer device according to an optional embodiment of the present disclosure. As shown in FIG. 7, the computer device comprises one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components communicate and connect with each other by using different buses, and can be installed on a common mainboard or in other manners as needed. The processor can process instructions executed in the computer device, including instructions stored in the memory or a graphical information of a GUI stored in the memory to display on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple storages. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).

[0110] The processor 10 can be a central processing unit, a network processing unit, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a generic array logic, or any combination thereof.

[0111] The memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods illustrated in the above embodiments.

[0112] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system and applications required by at least one function. The data storage area can store data created by the use of the computer device according to the presentation of a small program landing page, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some optional embodiments, the memory 20 can optionally include a memory disposed remotely relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0113] The memory 20 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned types of memories.

[0114] The computer device further includes a communication interface 30 for communication of the computer device with other devices or communication networks.

[0115] The embodiments of the present disclosure further provide a computer readable storage medium, and the method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or recorded in a storage medium, or be implemented as computer code originally stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, processor, microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, processor or hardware, the method shown in the above embodiments is implemented.

[0116] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present disclosure, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A resource processing method based on edge computing, wherein the method is applied to an edge cloud computing system, the method comprising: Obtain the resource processing request received by the target resource processing interface, wherein the target resource processing interface is any one of multiple different types of resource processing interfaces, and the resource processing request includes key information and resource description information; Use the aforementioned key information to locate the corresponding computer room in the computer room database; Resource processing operations are performed on the computer room based on the processing logic of the target resource processing interface and the resource description information.

2. The method according to claim 1, wherein the resource processing operation performed on the computer room based on the processing logic of the target resource processing interface and the resource description information includes: When the target resource processing interface is a resource planning interface, the filtering conditions and combination conditions are determined based on the processing logic of the resource planning interface. Multiple data center combinations can be obtained by combining the data centers according to the aforementioned combination conditions; From the data center combinations, obtain candidate data center combinations that meet the filtering criteria; The candidate data center combination is evaluated according to the preset evaluation strategy in the resource description information to obtain the index value corresponding to the candidate data center, and the candidate data center combination with the highest index value is taken as the target data center combination. Obtain the first resource information of each target data center in the target data center combination; Based on the first resource situation, resource planning information is generated and sent to the requester corresponding to the resource processing request.

3. The method according to claim 1, wherein the resource processing operation performed on the computer room based on the processing logic of the target resource processing interface and the resource description information includes: When the target resource processing interface is a resource request interface, the second resource status in the resource pool is determined based on the processing logic of the resource request interface; Check whether the second resource condition meets the resource description information, and obtain the check result; Based on the inspection results, perform resource processing operations on the computer room; The resource processing operations performed on the computer room based on the inspection results include: If the inspection result indicates that the second resource condition does not meet the resource description information, a first feedback result is sent to the requester corresponding to the resource processing request. The first feedback result includes resource application failure and the reason for failure. Alternatively, if the inspection result indicates that the second resource condition meets the resource description information, a second feedback result is sent to the requester corresponding to the resource processing request. The second feedback result includes resource application success and resource allocation information.

4. The method according to claim 1, wherein the resource processing operation performed on the computer room based on the processing logic of the target resource processing interface and the resource description information includes: When the target resource processing interface is a resource release interface, the resource to be released corresponding to the resource description information is determined based on the processing logic of the resource release interface; Detect whether the resource to be released exists in the computer room; If the resource to be released exists in the computer room, a release operation is performed on the resource to be released, a resource release result is obtained, and the resource release result is sent to the requester corresponding to the resource processing request.

5. The method according to claim 1, further comprising: Obtain instance load data for each region in the edge cloud computing system; Identify the target instance whose load data meets the expansion conditions, and query the first region where the original data center corresponding to the target instance is located; Check whether the available resources in the first region support the expansion operation; If the available resources support the expansion operation, obtain instance planning information and perform the expansion operation on the first region according to the instance planning information.

6. The method according to claim 5, further comprising: If the available resources do not support the expansion operation, an alarm message is generated; Obtain resource adjustment information based on the alarm information feedback; The available resources in the first region are adjusted according to the resource adjustment information until the available resources in the first region support the expansion operation.

7. The method according to claim 1, further comprising: Obtain a list of abnormal instances in the edge cloud computing system, wherein the list of abnormal instances includes abnormal instances from each data center; Obtain the exception time corresponding to each exception instance, and take the exception instances whose exception time exceeds the preset time as the target exception instances; Detect the available resources in the original data center corresponding to the target abnormal instance; If the available resources in the original data center do not meet the preset conditions, a new data center is added in the second area, wherein the second area is the area where the original data center is located; The newly added data center is expanded, and the target abnormal instance in the original data center is reduced in size.

8. A resource scheduling device based on edge computing, comprising: The acquisition module is used to acquire resource processing requests received by the target resource processing interface, wherein the target resource processing interface is any one of multiple different types of resource processing interfaces, and the resource processing request includes key information and resource description information. The search module is used to locate the corresponding data center from the data center database using the key information. The execution module is used to perform resource processing operations on the computer room based on the processing logic of the target resource processing interface and the resource description information.

9. A computer device, comprising: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 7.

Images