Cache space adjustment method and device, computer equipment and readable storage medium

Abstract

The invention relates to a cache space adjustment method and device, computer equipment and a readable storage medium, and relates to the technical field of communication. The method comprises the following steps: acquiring a bandwidth utilization rate of an edge node in the cloud edge collaborative network and service quality information of a service corresponding to the edge node; the edge node is provided with a cache space for caching service data of a service corresponding to the edge node; and under the condition that the bandwidth utilization rate or the service quality information triggers a preset cache adjustment condition, according to the triggered cache adjustment condition, clearing cache data in a cache space of the edge node, or expanding the cache space of the edge node. By adopting the method, the service quality of the edge node to the business can be improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for adjusting cache space. Background Technology

[0002] In a cloud-regional center-edge node collaborative network, typically, the edge node receives a service request initiated by the service initiator. The edge node then queries its cache for the corresponding service data and returns it to the service initiator. If the edge node does not find the service data in its cache, it sends a data retrieval request to the regional center to retrieve the service data from the regional center's cache and return it to the service initiator. Similarly, upon receiving a data retrieval request, the regional center queries its cache for the corresponding service data and returns it to the edge node. If the regional center does not find the service data in its cache, it sends a data retrieval request to the cloud to retrieve the service data from the cloud's cache and return it to the edge node.

[0003] In related technologies, the cache space of edge nodes is configured with a fixed size. When there is a sudden surge in traffic, the cache hit rate of edge nodes will drop sharply, resulting in a lower service quality of edge nodes for businesses. Summary of the Invention

[0004] Therefore, it is necessary to provide a cache space adjustment method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the service quality of edge nodes during traffic bursts, in order to address the aforementioned technical problem of low service quality of edge nodes for services.

[0005] Firstly, this application provides a method for adjusting cache space, including:

[0006] The bandwidth utilization rate of edge nodes in the cloud-edge collaborative network and the quality of service information of the services corresponding to the edge nodes are obtained; the edge nodes are equipped with cache space to cache the service data of the services corresponding to the edge nodes.

[0007] When the bandwidth utilization or the quality of service information triggers a preset cache adjustment condition, the cached data in the cache space of the edge node is cleared or the cache space of the edge node is expanded according to the triggered cache adjustment condition.

[0008] Secondly, this application also provides a cache space adjustment device, comprising:

[0009] The acquisition device is used to acquire the bandwidth utilization rate of edge nodes in the cloud-edge collaborative network and the service quality information of the services corresponding to the edge nodes; the edge nodes are equipped with cache space for caching the service data of the services corresponding to the edge nodes;

[0010] The adjustment device is used to clear cached data in the cache space of the edge node or expand the cache space of the edge node according to the triggered cache adjustment conditions when the bandwidth utilization or the quality of service information triggers preset cache adjustment conditions.

[0011] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0012] The bandwidth utilization rate of edge nodes in the cloud-edge collaborative network and the quality of service information of the services corresponding to the edge nodes are obtained; the edge nodes are equipped with cache space to cache the service data of the services corresponding to the edge nodes.

[0013] When the bandwidth utilization or the quality of service information triggers a preset cache adjustment condition, the cached data in the cache space of the edge node is cleared or the cache space of the edge node is expanded according to the triggered cache adjustment condition.

[0014] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0015] The bandwidth utilization rate of edge nodes in the cloud-edge collaborative network and the quality of service information of the services corresponding to the edge nodes are obtained; the edge nodes are equipped with cache space to cache the service data of the services corresponding to the edge nodes.

[0016] When the bandwidth utilization or the quality of service information triggers a preset cache adjustment condition, the cached data in the cache space of the edge node is cleared or the cache space of the edge node is expanded according to the triggered cache adjustment condition.

[0017] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0018] The bandwidth utilization rate of edge nodes in the cloud-edge collaborative network and the quality of service information of the services corresponding to the edge nodes are obtained; the edge nodes are equipped with cache space to cache the service data of the services corresponding to the edge nodes.

[0019] When the bandwidth utilization or the quality of service information triggers a preset cache adjustment condition, the cached data in the cache space of the edge node is cleared or the cache space of the edge node is expanded according to the triggered cache adjustment condition.

[0020] The aforementioned cache space adjustment method, apparatus, computer equipment, computer-readable storage medium, and computer program product, based on the bandwidth utilization of the edge node and the service quality information of the service corresponding to the edge node, can directly and dynamically increase the remaining available space in the cache space by expanding the node cache space, or indirectly and dynamically increase the remaining available space in the cache space by clearing cache data. This avoids a sharp drop in cache hit rate caused by the fixed configuration of the cache space size of the edge node, thus improving the service quality of the edge node for the service. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a diagram illustrating the application environment of a cache space adjustment method in one embodiment.

[0023] Figure 2 This is a flowchart illustrating a cache space adjustment method in one embodiment;

[0024] Figure 3 This is a schematic diagram of a cache space adaptive adjustment method based on service demand and network status in one embodiment;

[0025] Figure 4 This is a structural block diagram of a cache space adjustment device in one embodiment;

[0026] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0028] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "or," used in this application, refers to one of the embodiments, or any combination of multiple embodiments.

[0029] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0030] The cache space adjustment method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the application environment is a cloud-edge collaborative network, including a cloud 102, regional centers 104, and edge nodes 106. The cloud 102, regional centers 104, and edge nodes 106 communicate with each other through a network. The cloud-edge collaborative network includes a cloud 102, which manages multiple regional centers 104, and each regional center 104 manages multiple edge nodes 106. The cloud 102, regional centers 104, and edge nodes 106 can all be implemented through servers, terminals, or systems including servers and terminals. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing cloud computing services. Terminals can be, but are not limited to, various IoT devices, portable wearable devices, IoT gateways, smart sensors, personal computers, laptops, smartphones, tablets, drones, and low-altitude aircraft, etc. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle devices, projection devices, etc., and portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0031] In a specific application, edge node 106 is used to receive business requests initiated by the business initiator, query the business data corresponding to the business request in its cache space and return the business data to the business initiator. If edge node 106 does not find the business data in its cache space, it sends a data retrieval request for the business data to the corresponding regional center 104, so as to pull the business data from the cache space of the regional center 104 for caching and return the business data to the business initiator.

[0032] The regional center 104 is used to query the business data corresponding to the data acquisition request in its cache space and return the business data to the edge node 106 when it receives a data acquisition request from the edge node 106. If the business data is not found in its cache space, it sends a data acquisition request to the corresponding cloud 102 to pull the business data from the cache space of the cloud 102 and return the business data to the edge node 106.

[0033] Cloud 102 is used to retrieve business data from its cache space and return the business data to the regional center 104 when it receives a data retrieval request from the regional center 104.

[0034] Specifically, the regional center 104 in the cloud-edge collaborative network obtains the bandwidth utilization rate and service quality information of the edge node 106 in the cloud-edge collaborative network; the edge node 106 is equipped with a cache space to cache the service data of the service corresponding to the edge node 106; when the bandwidth utilization rate or service quality information triggers the preset cache adjustment conditions, the regional center 104 expands the cache space of the edge node 106 or clears the cached data in the cache space of the edge node 106 according to the triggered cache adjustment conditions.

[0035] In one exemplary embodiment, such as Figure 2 As shown, a cache space adjustment method is provided, which can be applied to, for example... Figure 1 The cloud-edge collaborative network shown is used as an example for illustration, including the following steps S202 to S204. Wherein:

[0036] Step S202: Obtain the bandwidth utilization rate of edge nodes and the service quality information of the services corresponding to the edge nodes in the cloud-edge collaborative network.

[0037] The edge nodes are equipped with cache space to cache the business data of the corresponding services.

[0038] Each edge node corresponds to at least one type of service.

[0039] Among them, bandwidth utilization is the ratio between the used bandwidth of the edge node and the bandwidth.

[0040] Service quality information is used to characterize the service quality requirements of a service and the corresponding service quality (QoS) of the edge node. In practical applications, service quality information includes at least the service quality requirement level of the service and the service quality index value of the edge node corresponding to the service under preset service quality indicators. In practical applications, service quality indicators are used to evaluate QoS.

[0041] Specifically, each edge node in the cloud-edge collaborative network collects bandwidth utilization and corresponding service quality information in real time, and reports the bandwidth utilization and corresponding service quality information to its corresponding regional center in the cloud-edge collaborative network; each regional center in the cloud-edge collaborative network obtains the bandwidth utilization and corresponding service quality information of each edge node it manages.

[0042] Step S204: When bandwidth utilization or service quality information triggers preset cache adjustment conditions, the cached data in the cache space of the edge node is cleared or the cache space of the edge node is expanded according to the triggered cache adjustment conditions.

[0043] Specifically, in the cloud-edge collaborative network, each regional center can, when the bandwidth utilization or quality of service information of the edge nodes under its management triggers the preset cache adjustment conditions, clear the cached data in the cache space of the edge nodes, or expand the cache space of the edge nodes to increase the remaining available space in the cache space.

[0044] The cache adjustment conditions include a first type of adjustment condition for expanding the cache space of edge nodes and a second type of adjustment condition for clearing cached data in the cache space of edge nodes. In practical applications, both types of adjustment conditions can be triggered simultaneously.

[0045] In related technologies, the cache space size of edge nodes is configured in a fixed way. When there is a sudden surge in traffic, the cache hit rate of edge nodes will drop sharply. The cache hit rate of edge nodes is used to represent the number of times business data is retrieved in the node cache. When the cache hit rate of edge nodes drops sharply, the edge nodes need to consume network resources to pull business data from the regional center and the cloud, which leads to increased resource consumption and response time of edge nodes, thus affecting the service quality of the business.

[0046] In the above-mentioned cache space adjustment method, based on the bandwidth utilization of the edge node and the service quality information of the service corresponding to the edge node, the remaining available space in the cache space can be dynamically increased directly by expanding the node cache space, or indirectly by clearing cache data. This avoids the sharp drop in cache hit rate caused by the fixed configuration of the edge node cache space size, thus improving the service quality of the edge node for the service.

[0047] In one exemplary embodiment, the number of services is at least one.

[0048] In this embodiment, the cache adjustment conditions include a first type of adjustment condition for expanding the cache space of edge nodes.

[0049] The cache space adjustment method provided in this application further includes the following steps for determining the triggered cache adjustment conditions: determining the cache priority of each service based on the service quality information of each service; and determining that the first type of adjustment condition is triggered when the cache priority of any service in each service is greater than or equal to the cache priority threshold.

[0050] Specifically, for each managed edge node, the regional center determines the cache priority of each service based on the service quality information of each service corresponding to that edge node. If the cache priority of any service is greater than or equal to the preset cache priority threshold, the first type of adjustment condition for expanding the cache space of the edge node is triggered, thus triggering the expansion of the cache space of the edge node.

[0051] In this embodiment, the regional center can expand the cache space of the edge nodes according to the service quality information of each service provided by the edge nodes, thereby realizing the dynamic adjustment of the cache space of the edge nodes. This avoids the sharp drop in cache hit rate caused by the fixed configuration of the cache space size of the edge nodes, thus improving the service quality of the edge nodes for the services.

[0052] In one exemplary embodiment, the cloud-edge collaborative network also includes a regional center.

[0053] The above steps expand the cache space of the edge nodes, specifically including the following steps: controlling the edge nodes to send expansion requests to the regional center.

[0054] The regional center is used to determine the cache space to be allocated to the edge nodes based on the number of expansion requests received from each edge node and the space utilization rate of the regional center's cache space; the cache space determined by the regional center is then allocated to the edge nodes to expand the cache space of the edge nodes.

[0055] Space utilization rate is the ratio between the size of the used space in the cache space of the region center and the size of the cache space of the region center.

[0056] Specifically, when the first type of adjustment condition is triggered, the regional center controls the edge node to send an expansion request to the regional center. Upon receiving an expansion request from any edge node, the regional center first determines the number of expansion requests received simultaneously from different edge nodes, as well as the space utilization rate of the central cache. Then, based on the number of expansion requests received simultaneously and the space utilization rate of the central cache, the regional center determines whether to expand the node's cache space.

[0057] In this embodiment, the regional center can determine whether to expand the cache space of the edge nodes based on the number of expansion requests received at the same time and the space utilization rate of its cache space, thereby realizing dynamic adjustment of the cache space of the edge nodes and avoiding a sharp drop in cache hit rate due to the fixed configuration of the cache space size of the edge nodes, thus improving the service quality of the edge nodes for services.

[0058] In one exemplary embodiment, the cloud-edge collaborative network also includes a cloud.

[0059] The regional center is also used to determine the cache space allocated to edge nodes when the number of requests is less than or equal to the request number threshold and the space utilization rate is less than the space utilization rate threshold; and to pull hot business data from the cloud and cache it in the cache space of the regional center when the number of requests is greater than the request number threshold and the space utilization rate is less than the space utilization rate threshold.

[0060] Specifically, if the number of expansion requests received by the regional center at the same time is less than or equal to a preset request number threshold, and the space utilization rate of the regional center's cache space is less than a preset space utilization rate threshold, or the space utilization rate of the regional center's cache space is less than a preset space utilization rate threshold, then the regional center allocates part of its cache space to the edge nodes to expand the edge nodes.

[0061] If the number of expansion requests received by the regional center during the same period exceeds a preset request threshold, and the cache space utilization rate of the regional center is less than a preset space utilization threshold, or the cache space utilization rate of the regional center is less than a preset space utilization threshold, then the regional center will initiate "hot data sinking," pulling hot business data from the cloud and caching it in the regional center's cache space. Hot business data refers to business data with a high corresponding popularity value, such as business data with a popularity value greater than or equal to a preset popularity threshold, or business data ranking high in popularity.

[0062] If the number of expansion requests received by the regional center at the same time is less than or equal to a preset request number threshold, and the space utilization rate of the regional center's cache space is greater than or equal to a preset space utilization rate threshold, or if the number of expansion requests received by the regional center at the same time is greater than a preset request number threshold, and the space utilization rate of the regional center's cache space is greater than or equal to a preset space utilization rate threshold, or if the space utilization rate of the regional center's cache space is greater than or equal to a preset space utilization rate threshold, the regional center will reject the expansion request from the edge node and will not take any action because it has no remaining cache resources and cannot meet the expansion requirements.

[0063] For example, suppose the preset request quantity threshold is 3 and the preset space utilization threshold is 70%; if the request quantity is ≤3 and the space utilization of the regional center's cache space is <70%, then the regional center will expand the edge nodes; if the request quantity is >3 and the space utilization of the regional center's cache space is <70%, then the regional center will initiate "hot data sinking"; otherwise, the regional center will reject the expansion requests of the edge nodes and will not take any action.

[0064] In this embodiment, the regional center can determine whether to expand the cache space of the edge nodes based on the number of expansion requests received at the same time and the space utilization rate of its cache space, thereby realizing dynamic adjustment of the cache space of the edge nodes and avoiding a sharp drop in cache hit rate due to the fixed configuration of the cache space size of the edge nodes, thus improving the service quality of the edge nodes for services.

[0065] In an exemplary embodiment, the popularity value of business data is calculated by a regional center or the cloud. The calculation process of the popularity value of business data is as follows: the cloud or regional center counts the access volume of each business data and calculates the popularity value of each business data based on the access volume of each business data.

[0066] In one exemplary embodiment, the service quality information includes at least the service quality requirement level of the service and the service quality index value of the edge node corresponding to the service under the preset service quality index.

[0067] Each service has a corresponding service quality requirement level, which is used to characterize the level of service quality requirements of each service. For example, in this embodiment, the service quality requirement levels are divided into gold, silver and bronze levels from high to low, and the service quality requirements corresponding to different service quality requirement levels are different.

[0068] The service quality metrics include at least one of the following: edge node bandwidth, edge node packet loss rate, service latency, and service cache hit rate under node caching.

[0069] The packet loss rate is the ratio of the number of lost packets to the total number of packets sent (by the edge nodes). In practical applications, a packet can be a packet sent by an edge node to the service initiator, or a packet sent by an edge node to the regional center, such as a heartbeat packet.

[0070] Among them, business latency refers to the delay from the business initiator to the cloud-edge collaborative network (any one of the edge nodes, regional centers, or the cloud).

[0071] Among them, cache hit means that the business data of the business can be found in the node cache, that is, the business data of the business is cached in the node cache; cache miss means that the business data of the business cannot be found in the node cache, that is, the business data of the business is not cached in the node cache.

[0072] The cache hit rate is the ratio between the number of cache hits and the total number of queries (for querying business data at edge nodes).

[0073] The above steps, which determine the cache priority of each service based on the service quality information of each service, specifically include the following steps: obtaining the current level weight and the current indicator weight of different service quality requirement levels; for each service, merging the service quality requirement level and service quality indicator value according to the level weight of the service quality requirement level and the indicator weight of the service quality indicator to obtain the cache priority of the service.

[0074] The grade weight and indicator weight are determined based on the service quality default rate of each business corresponding to the edge node.

[0075] Each service has corresponding service quality conditions under each service quality indicator. In practical applications, the service quality conditions for each service are related to the service quality requirement level of that service; different service quality requirement levels correspond to different service quality conditions. In practical applications, service quality conditions at least include service quality indicator thresholds.

[0076] The service quality default rate (SQFR) for edge node services represents the number of times a service's service quality indicator fails to meet the corresponding service quality conditions. In practical applications, the SQFR is the ratio of the number of SQFR defaults to the total number of service calls made by the edge node.

[0077] Specifically, the regional center obtains the current level weights of different service quality requirement levels and the current indicator weights of each service quality indicator from the cloud; then, for each service corresponding to each edge node, the regional center performs weighted fusion processing on the service quality requirement level of the service and the indicator weights of each service quality indicator of the edge node for the corresponding service to obtain the cache priority of the service.

[0078] For example, the regional center calculates the cache priority of services using the following formula:

[0079]

[0080] in, Prioritize caching for specific business logic; The service quality requirement level for the business. The current weight of the service quality requirement level for the business; This refers to the actual business latency under the service quality indicator "business latency". The service quality condition "maximum service latency" is the service quality indicator "service latency" corresponding to the business. The current weight of the service quality indicator "Business Latency"; This represents the actual cache hit rate of the business under the service quality metric "cache hit rate". The current weight of the service quality metric "Cache Hit Rate".

[0081] In this embodiment, the regional center can quantify the caching priority of services by using the service quality requirement level and service quality index value of services. This allows for dynamic adjustment of the cache space of edge nodes, avoiding a sharp drop in cache hit rate due to the fixed configuration of the cache space size of edge nodes. Therefore, the service quality of edge nodes for services is improved.

[0082] In an exemplary embodiment, the cloud collects the service quality default rate of each service corresponding to each edge node in the cloud-edge collaborative network, and dynamically updates the level weight and indicator weight according to a preset time interval (e.g., hourly) and the service quality default rate of each service corresponding to each edge node.

[0083] In one exemplary embodiment, the cache adjustment conditions also include a second type of adjustment conditions for clearing cached data in the cache space of edge nodes.

[0084] The cache space adjustment method provided in this application further includes the following steps for determining the triggered cache adjustment conditions: determining a bandwidth utilization threshold based on the bandwidth of the edge node; and determining that a second type of adjustment condition is triggered when the bandwidth utilization is greater than the bandwidth utilization threshold.

[0085] Specifically, for each managed edge node, the regional center determines the bandwidth utilization threshold corresponding to the edge node based on the bandwidth of the edge node; then, when the bandwidth utilization of the edge node is greater than the bandwidth utilization threshold, the regional center determines that the second type of adjustment condition for clearing the cached data in the cache space of the edge node is triggered, thus triggering the clearing of the cached data in the cache space of the edge node, and the regional center controls the edge node to clear its cached data.

[0086] In practical applications, if the bandwidth is greater than or equal to the first preset bandwidth, the region center determines the bandwidth utilization threshold as the first bandwidth utilization threshold; if the bandwidth is less than the second preset bandwidth, the region center determines the bandwidth utilization threshold as the second bandwidth utilization threshold; wherein, the first preset bandwidth is greater than the second preset bandwidth, and the first bandwidth utilization threshold is greater than the second bandwidth utilization threshold.

[0087] For example, if the bandwidth is ≥100Mbps, the regional center determines the bandwidth utilization threshold to be 75%; if the bandwidth is <50Mbps, the regional center determines the bandwidth utilization threshold to be 60%.

[0088] In this embodiment, the regional center can clear the cached data of the edge nodes based on the bandwidth and bandwidth utilization of the edge nodes, thereby realizing the dynamic adjustment of the remaining available cache space of the edge nodes. This avoids the sharp drop in cache hit rate caused by the fixed configuration of the cache space size of the edge nodes, thus improving the service quality of the edge nodes for services.

[0089] In one exemplary embodiment, there is at least one service; each service has a corresponding service quality requirement level, which is used to characterize the level of service quality requirements of each service; for example, in this embodiment, the service quality requirement levels are divided into gold, silver and bronze levels from high to low, and the service quality requirements corresponding to different service quality requirement levels are different.

[0090] In this embodiment, the cache space of the edge node is preset with a first cache queue and a second cache queue; the first cache queue is used to cache service data whose service quality requirement level is higher than or equal to the first level threshold and whose access count is greater than or equal to the access count threshold; the second cache queue is used to cache service data whose service quality requirement level is lower than or equal to the second level threshold; the first level threshold is higher than the second level threshold.

[0091] In practical applications, the first cache queue uses the LRU-K algorithm (an improved version of the Least Recently Used algorithm) to cache the business data of gold-level services that have been accessed 3 times or more; the second cache queue uses the FIFO algorithm (First Input First Output) to cache the business data of bronze-level services.

[0092] Furthermore, the first cache queue includes a historical queue and a cache queue. Business data for gold-level services is first cached in the historical queue. Business data accessed ≥3 times in the historical queue will be migrated to the head of the cache queue by the edge nodes.

[0093] The above steps clear the cached data in the cache space of the edge node, specifically including the following steps: clearing the business data with the earliest recent access time in the first cache queue; clearing the business data in the second cache queue whose time interval between the recent access time and the current time is greater than or equal to the time interval threshold.

[0094] Specifically, for the first cache queue, the edge node clears the business data with the earliest recent access time from its cached business data; for the second cache queue, the edge node clears the business data with the latest access time and the current time being greater than or equal to the time interval threshold, such as business data that has not been accessed for 24 hours.

[0095] In this embodiment, the edge node clears the cached business data of each business according to the service quality requirements level of different services, thereby realizing the dynamic adjustment of the remaining available cache space of the edge node. This avoids the sharp drop in cache hit rate caused by the fixed configuration of the cache space of the edge node, thus improving the service quality of the edge node for the business.

[0096] In an exemplary embodiment, the cache space adjustment method provided in this application further includes the following steps for pre-expanding and allocating cached data for edge nodes: predicting the service traffic of edge nodes in future time intervals using a pre-trained service traffic prediction model to obtain the service traffic prediction results of edge nodes; increasing the cache space of edge nodes based on the service traffic prediction results, and caching the service data of services with sudden traffic surges in the service traffic prediction results to the cache space of edge nodes.

[0097] The business traffic forecast results include at least the business traffic forecast values ​​for each business and the business experiencing a traffic surge; the business experiencing a traffic surge is the business whose corresponding business traffic forecast value suddenly increases.

[0098] Specifically, during off-peak periods, the cloud uses a business traffic prediction model trained in advance using reinforcement learning to predict the business traffic of edge nodes during future peak periods. This results in predicted business traffic for edge nodes during peak periods, such as the predicted business traffic for each business corresponding to the edge node and the business experiencing a surge in traffic within each business. Then, based on the predicted business traffic for each business corresponding to the edge node during peak periods, the cloud pre-increases the cache space of the edge nodes and pre-caches the business data of the business experiencing a surge in traffic into the cache space of the edge nodes.

[0099] In practical applications, the cloud first sends the business data of the surge in traffic to the regional center, and then the regional center sends it to the edge nodes.

[0100] In this embodiment, by predicting business traffic, edge nodes can be expanded and corresponding business data can be allocated in advance, which helps to improve the cache hit rate of edge nodes during peak business periods, thereby improving the service quality of edge nodes for business.

[0101] In one exemplary embodiment, edge nodes retrieve the latest business data for a given service from the regional center or the cloud and cache it based on the service weight of the business data they store. The higher the service weight, the more frequently the edge node retrieves the latest business data. In specific applications, edge nodes, regional centers, or the cloud dynamically update the service weights of each service using an exponentially weighted moving average. The service weight is related to the time of the most recent retrieval of service data; the earlier the most recent retrieval, the lower the service weight, and vice versa.

[0102] In one exemplary embodiment, the cloud is also used to implement the sharding of business data using a consistent hashing algorithm to ensure load balancing of business data across regional centers and edge nodes.

[0103] In an exemplary embodiment, when the space utilization rate of the cache space in any regional center is >85%, the cloud generates a global policy based on the reinforcement learning model, issues a mirror migration instruction to the regional center, migrates redundant content to other regional centers, and releases the space of that regional center.

[0104] To more clearly illustrate the cache space adjustment method provided in the embodiments of this application, the following specific embodiment is used to describe the cache space adjustment method in detail. However, it should be understood that the embodiments of this application are not limited thereto. Figure 3 As shown, in one exemplary embodiment, this application also provides a method for adaptive adjustment of cache space based on service demand and network status, specifically including the following steps:

[0105] 1. Information collection and reporting.

[0106] Edge nodes collect their own bandwidth utilization, the corresponding service quality requirements level of each service, and the service quality index values, and report them to the regional center.

[0107] 2. Data processing.

[0108] The regional center receives and reports data, summarizes it, and stores it in the "Business-Network Mapping Table," which supports microsecond-level queries.

[0109] 3. Calculate cache priority.

[0110] The regional center calculates the cache priority of each service on the edge node based on the service quality requirement level and service quality index values ​​of each service. If the cache priority of any service on the edge node is greater than the cache priority threshold, the center will trigger a capacity expansion.

[0111] 4. Issuance of expansion command.

[0112] The regional center sends expansion commands to the edge nodes.

[0113] 5. Insufficient capacity.

[0114] If the expansion of edge nodes still cannot meet the demand, and the cache utilization rate of the regional center is less than 70%, the cloud will pre-push high-frequency content fragments to the regional center to reduce edge back-to-origin requests.

[0115] 6. Mirror migration.

[0116] When the cloud cache utilization rate in a certain regional center is greater than 85%, a global strategy is generated based on a reinforcement learning model. By issuing a "mirror migration command", redundant content is migrated to other regional centers to free up space.

[0117] 7. Cache is dynamically adjusted.

[0118] Edge nodes manage caches using a dual-queue strategy based on the ABCA algorithm (Adaptive Buffer Coordination Algorithm, a network architecture centered on information (data, resources, services, etc.), which enables communication by assigning unique identifiers to all resources (rather than relying on device geographic location), supports the forwarding, caching, and management of named data objects, and is suitable for heterogeneous resource collaboration scenarios): Gold-level services use the LRU-K (K=3) algorithm to retain the service data accessed the most recently 3 times; Bronze-level services use the FIFO algorithm to automatically clean up service data that has not been accessed for more than 24 hours.

[0119] 8. Global optimization.

[0120] The cloud collects anonymized historical data from regional centers (e.g., "the hit rate of educational content surges by 40% at 10 AM on weekends") and trains a reinforcement learning model to predict traffic trends. Based on the prediction results, the cloud pre-allocates elastic cache space to edge nodes before peak business periods (e.g., 2 hours before a live event) and issues a "preheating command": pulling data from the regional center to the edge to improve the cache hit rate of edge nodes.

[0121] 9. State synchronization.

[0122] The regional center synchronizes decision results to the cloud every 100ms. The cloud verifies version continuity and ensures data consistency through an "identifier-status linkage" mechanism.

[0123] In this embodiment, both resource utilization and service quality are improved: Compared to traditional static cache allocation, by dynamically adapting to service quality requirements and network conditions (bandwidth, latency), edge cache utilization is improved, reducing latency for high-priority services and minimizing resource idleness and service lag. Cross-layer collaboration reduces redundancy costs: An innovative mechanism allows edge nodes to temporarily borrow cache from the regional center, combined with "hot data sinking" and cloud-based global scheduling, avoiding duplicate caching (e.g., live event content is only stored collaboratively between the regional center and the edge), thus reducing network transmission costs. By constructing a three-layer collaborative architecture of edge nodes-regional center-cloud, and combining dynamic resource allocation algorithms with dual-dimensional decisions based on service quality requirements and network conditions, elastic scaling and precise scheduling of cache space are achieved, improving resource utilization and service stability.

[0124] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0125] Based on the same inventive concept, this application also provides a cache space adjustment apparatus for implementing the cache space adjustment method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more cache space adjustment apparatus embodiments provided below can be found in the limitations of the cache space adjustment method described above, and will not be repeated here.

[0126] In one exemplary embodiment, such as Figure 4 As shown, a cache space adjustment device is provided, including: an acquisition device 402 and an adjustment device 404, wherein:

[0127] The acquisition device 402 is used to acquire the bandwidth utilization rate of edge nodes and the service quality information of the services corresponding to the edge nodes in the cloud-edge collaborative network; the edge nodes are equipped with cache space to cache the service data of the services corresponding to the edge nodes.

[0128] The adjustment device 404 is used to clear cached data in the cache space of the edge node or expand the cache space of the edge node according to the triggered cache adjustment conditions when the bandwidth utilization or service quality information triggers preset cache adjustment conditions.

[0129] In one exemplary embodiment, the number of services is at least one; the cache adjustment conditions include a first type of adjustment conditions for expanding the cache space of edge nodes.

[0130] The adjustment device 404 is also used to determine the cache priority of each service based on the service quality information of each service; and to determine that the first type of adjustment condition is triggered when the cache priority of any service is greater than or equal to the cache priority threshold.

[0131] In one exemplary embodiment, the cloud-edge collaborative network also includes a regional center.

[0132] The adjustment device 404 is also used to control the edge nodes to send expansion requests to the regional center; the regional center is used to determine the cache space to be allocated to the edge nodes in the cache space of the regional center based on the number of expansion requests received from each edge node and the space utilization rate of the cache space of the regional center; and to allocate the cache space determined by the regional center to the edge nodes to realize the expansion of the cache space of the edge nodes.

[0133] In one exemplary embodiment, the cloud-edge collaborative network also includes a cloud. The regional center is further configured to determine the cache space to be allocated to the edge nodes when the number of requests is less than or equal to a request number threshold and the space utilization rate is less than a space utilization rate threshold; and to pull hot service data from the cloud and cache it in the cache space of the regional center when the number of requests is greater than the request number threshold and the space utilization rate is less than the space utilization rate threshold.

[0134] In one exemplary embodiment, the service quality information includes at least the service quality requirement level of the service and the service quality index value of the edge node corresponding to the service under the preset service quality index.

[0135] The adjustment device 404 is also used to obtain the current level weight and the current indicator weight of different service quality demand levels; the level weight and indicator weight are determined based on the service quality default rate of each service corresponding to the edge node; each service has corresponding service quality conditions under the service quality indicator, and the service quality default rate of the service corresponding to the edge node is used to characterize the number of times the service quality indicator value of the service does not meet the corresponding service quality conditions; for each service, the service quality demand level and service quality indicator value of the service are fused according to the level weight of the service quality demand level and the indicator weight of the service quality indicator to obtain the cache priority of the service.

[0136] In one exemplary embodiment, the cache adjustment conditions also include a second type of adjustment conditions for clearing cached data in the cache space of edge nodes.

[0137] The adjustment device 404 is also used to determine a bandwidth utilization threshold based on the bandwidth of the edge node; and to determine that a second type of adjustment condition is triggered when the bandwidth utilization is greater than the bandwidth utilization threshold.

[0138] In one exemplary embodiment, each service has a corresponding service quality requirement level; the cache space of the edge node is preset with a first cache queue and a second cache queue; the first cache queue is used to cache service data whose service quality requirement level is higher than or equal to the first level threshold and whose access count is greater than or equal to the access count threshold; the second cache queue is used to cache service data whose service quality requirement level is lower than or equal to the second level threshold; the first level threshold is higher than the second level threshold;

[0139] The adjustment device 404 is also used to clear the service data with the earliest recent access time in the first cache queue; and to clear the service data in the second cache queue whose time interval between the recent access time and the current time is greater than or equal to the time interval threshold.

[0140] In an exemplary embodiment, the adjustment device 404 is further configured to predict the service traffic of the edge node in a future time interval using a pre-trained service traffic prediction model, and obtain the service traffic prediction result of the edge node; based on the service traffic prediction result, increase the cache space of the edge node, and cache the service data of the service with sudden traffic surge in the service traffic prediction result into the cache space of the edge node.

[0141] Each module in the aforementioned cache space adjustment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0142] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores business data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a cache space adjustment method.

[0143] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0145] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0146] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0147] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of adjusting cache space, the method comprising: The method comprises: acquiring bandwidth utilization of an edge node in a cloud-edge collaborative network and service quality information of a service corresponding to the edge node; the edge node is provided with a cache space for caching service data of the service corresponding to the edge node; in a case where the bandwidth utilization or the service quality information triggers a preset cache adjustment condition, clearing cache data in the cache space of the edge node or expanding the cache space of the edge node according to the triggered cache adjustment condition.

2. The method of claim 1, wherein, The number of services is at least one; the cache adjustment condition includes a first type of adjustment condition for expanding the cache space of the edge node; The method further comprises: determining a cache priority of each service according to the service quality information of each service; in a case where the cache priority of any one of the services is greater than or equal to a cache priority threshold, determining that the first type of adjustment condition is triggered.

3. The method of claim 2, wherein, The cloud-edge collaborative network further comprises a regional center; The expansion of the cache space of the edge node comprises: controlling the edge node to send an expansion request to the regional center; the regional center is used to determine cache space allocated to the edge node in the cache space of the regional center according to a request number of expansion requests received by each edge node and a space utilization of the cache space of the regional center; allocating the cache space determined by the regional center to the edge node to realize the expansion of the cache space of the edge node.

4. The method of claim 3, wherein, The cloud-edge collaborative network further comprises a cloud; The regional center is further used to determine cache space allocated to the edge node in a case where the request number is less than or equal to a request number threshold and the space utilization is less than a space utilization threshold; and in a case where the request number is greater than the request number threshold and the space utilization is less than the space utilization threshold, pulling hot service data from the cloud and caching the hot service data to the cache space of the regional center.

5. The method of claim 2, wherein, The service quality information at least includes a service quality requirement level of the service and a service quality index value of the service corresponding to the edge node under a preset service quality index; The determination of the cache priority of each service according to the service quality information of each service comprises: acquiring a current level weight of different service quality requirement levels and a current index weight of the service quality index; the level weight and the index weight are determined according to a service quality violation rate of the edge node corresponding to each service; each service has a corresponding service quality condition under the service quality index; the service quality violation rate of the edge node corresponding to the service represents a number of times that the service quality index value of the service does not meet the corresponding service quality condition. The service quality requirement level and the service quality indicator value of the service are fused according to the level weight of the service quality requirement level of the service and the indicator weight of the service quality indicator, to obtain the cache priority of the service.

6. The method of claim 1, wherein, The cache adjustment condition further includes a second type of adjustment condition for clearing cache data in the cache space of the edge node. The method further includes: determining a bandwidth utilization threshold according to the bandwidth of the edge node; determining that the second type of adjustment condition is triggered in a case where the bandwidth utilization is greater than the bandwidth utilization threshold.

7. The method of claim 6, wherein, The number of services is at least one; each service has a corresponding service quality requirement level; the cache space of the edge node is preconfigured with a first cache queue and a second cache queue; the first cache queue is used to cache service data of a service whose service quality requirement level is higher than or equal to a first level threshold and whose access frequency is greater than or equal to an access frequency threshold; and the second cache queue is used to cache service data of a service whose service quality requirement level is lower than or equal to a second level threshold. The first level threshold is higher than the second level threshold. The clearing of the cache data in the cache space of the edge node includes: clearing service data in the first cache queue that has the earliest corresponding recent access time; clearing service data in the second cache queue that has a time interval between the corresponding recent access time and the current time greater than or equal to a time interval threshold.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: predicting, by a pre-trained service traffic prediction model, service traffic of the edge node in a future time interval to obtain a service traffic prediction result of the edge node; increasing the cache space of the edge node according to the service traffic prediction result, and caching service data of a traffic surge service in the service traffic prediction result to the cache space of the edge node.

9. A cache space adjustment apparatus, characterized by comprising: The apparatus includes: an obtaining device configured to obtain bandwidth utilization of an edge node in a cloud-edge collaboration network and service quality information of services corresponding to the edge node; the edge node is provided with a cache space configured to cache service data of the services corresponding to the edge node; an adjusting device configured to, in a case where the bandwidth utilization or the service quality information triggers a preconfigured cache adjustment condition, clear cache data in the cache space of the edge node or expand the cache space of the edge node according to the triggered cache adjustment condition. 10.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-9. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 8.

12. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 8.

Images