Satellite-ground convergence network resource management and content collaborative caching method and system

Abstract

The invention discloses a satellite-ground convergence network resource management and content collaborative caching method and system, and belongs to the technical field of space communication, and the method comprises the steps: dynamically sensing the information of a current satellite-ground convergence network through employing a time slot division method; in a satellite-ground collaborative cache and content access application scene, a terminal user sends content request information through an access satellite node according to environment perception, the access satellite node searches current content cache information in the node firstly, and then performs cache content search in other satellite nodes in an inter-satellite collaborative mode; and finally, cache content search is performed in a ground cloud center in a satellite-ground cooperation mode, routing forwarding is performed through an inter-satellite link, and quick response of request content is realized as far as possible. By adopting the method based on satellite neighborhood search and satellite-ground cooperative access, the rapid access service capability of the satellite-ground cooperative and inter-satellite cooperative content cache machine is realized, the design complexity of the satellite-ground fusion network system is effectively reduced, and the operation effectiveness of the satellite-ground fusion network is improved.

Description

Technical Field

[0001] The invention relates to a satellite-ground fusion network resource management and content collaborative caching method and system, belonging to the field of space communication technology. Background Art

[0002] With the development of wireless communication technology and the increase of smart devices, ground networks with edge cache can provide Internet services such as multimedia services, Web services and application services to end users to improve user service experience and network operation utility, where cached content is as close to user access as possible to reduce data transmission delay and network bandwidth costs. It should be noted that content cache servers are usually located at the edge nodes of the ground network. However, due to high capital expenditures and harsh geographical environments, ground networks have not yet covered more than 80% of land areas and more than 95% of ocean areas. In this case, it is impossible to provide content services to remote end users who are not in areas covered by ground networks (such as oceans, deserts and mountains). As a supplement to ground networks, large low Earth Orbit (LEO) satellite constellations can provide global wireless communication and Internet access services to end users, and have become an important part of future communication systems.

[0003] Traditional satellite networks only have data routing and forwarding functions. End users need to access Internet services from the ground through satellite networks, resulting in high service delays and network load costs. Combined with the characteristics of seamless global coverage and low transmission latency of low-Earth orbit satellite networks, satellite edge caching, as a new paradigm, places cache servers on satellites to achieve edge caching services. However, the satellite network's onboard resources are very limited, and when a large number of end users arrive, they cannot meet the user's business needs. Combining the advantages of ground networks and satellite networks, it is a promising approach to carry out collaborative content caching in a satellite-ground fusion network to provide content services on demand to end users in a flexible and efficient manner. It is worth noting that unlike ground networks with relatively unchanged topology and abundant resources, due to the dynamic characteristics of satellites, the topology of satellite networks with strictly limited resources changes over time. Therefore, how to implement collaborative caching and resource allocation strategies in a satellite-ground fusion network is a challenging problem.

[0004] Regarding the satellite-ground fusion network and cache content access technology, by consulting existing literature and patents, the existing work has relatively simplified the complexity of collaborative caching and resource allocation problems in the satellite-ground fusion network, mainly considering the satellite-ground collaborative caching in the scenario without inter-satellite communication. In this case, due to the lack of inter-satellite collaborative caching, the performance of user service experience and network operation utility cannot be guaranteed. In addition, considering the inter-satellite communication capability of the low-orbit satellite network, collaborative caching services between different satellites can be provided to end users. It should be noted that since the available links, bandwidth and storage resources of the satellite network are limited, the user service experience and network operation utility can be improved by optimizing the collaborative caching and resource allocation strategy. However, the existing related work rarely discusses the joint optimization of data routing, network bandwidth and onboard storage resources of collaborative caching in the satellite-ground fusion network. Furthermore, with the increase in the number of satellites, the dimensional information of the space state will also increase accordingly, which will bring difficulties to the global resource management of the satellite-ground fusion network. It is necessary to further study the collaborative caching architecture of the satellite-ground fusion network to simplify the system complexity of resource management and improve the real-time nature of decision-making. Summary of the invention

[0005] The technical problem solved by the present invention is: to overcome the shortcomings of the prior art, to provide a satellite-ground fusion network resource management and content collaborative caching method and system, to construct a system model of satellite-ground collaborative caching and resource optimization, to realize the content service supply capability of satellite-ground collaboration and inter-satellite collaboration, to effectively reduce the design complexity of the satellite-ground fusion network system, and to improve the operation efficiency of the satellite-ground fusion network.

[0006] The technical solution of the present invention is: a satellite-ground integrated network resource management and content collaborative caching method, comprising:

[0007] Each satellite node in the satellite-ground fusion network obtains the random access request information of the user end in the current time slot in real time;

[0008] According to the time slot network model of the satellite-ground fusion network, the network status information is sensed and obtained in each time slot;

[0009] Based on the acquired network status information and random access request information, the ground operation control center establishes a satellite-ground integrated network resource management and content collaborative access system model, and builds a joint optimization mathematical model for network storage resources and network bandwidth resources under multiple physical constraints;

[0010] According to the satellite-ground fusion network resource management and content collaborative access system model, and the joint optimization mathematical model, the satellite-ground collaborative caching and resource configuration optimization method is used to determine the optimization strategy for completing satellite-ground collaborative caching, resource optimization configuration, and cache content access strategy selection, so as to minimize the satellite-ground network deployment cost;

[0011] The satellite-ground fusion network implements resource configuration and content cache deployment according to the optimization strategy, and provides cache content collaborative access services for the user end.

[0012] Furthermore, the satellite node only establishes a satellite-to-ground link with a user terminal within its coverage area, and provides network access services for the user terminal.

[0013] Furthermore, the network status information includes current location, network topology, task running status, resource usage, cache content type and task service requirements.

[0014] Furthermore, the establishment of the satellite-ground fusion network resource management and content collaborative access system model includes the bandwidth usage cost of user u during content access.

[0015]

[0016] And the storage resources generated when user u currently accesses the content

[0017]

[0018] Among them, x u,w = {0,1} indicates whether user u accesses content w, where x u,w =1 means user u accesses content w, otherwise x u,w =0; Indicates whether user u uses link e in the process of accessing content w, where indicates that user u used link e in the process of accessing content w, otherwise The actual data rate at which user u accesses content w is denoted as b u ; a u,dc = {0,1} indicates whether user u accesses content from the ground data center via the satellite network, a u,dc =1 means accessing content from the ground data center via the satellite network, otherwise a u,dc =0;y w,v = {0,1} indicates whether content w is deployed on satellite node v, where y w,v =1 means content w is deployed on satellite node v, otherwise y w,v =0; Indicates whether user u accesses content w through satellite node v, where Indicates that user u accesses content w, otherwise Content w data size representation s w .

[0019] Furthermore, the constraints of the satellite-ground fusion network resource management and content collaborative access system model include user access constraints

[0020]

[0021] and the storage resource constraints of satellite nodes when accessing content caches

[0022]

[0023] And the content w service delay of each user u does not exceed the maximum acceptable service delay

[0024]

[0025] And the access service constraints provided by each satellite node to users

[0026]

[0027] And bandwidth resource constraints

[0028]

[0029] And the in-degree and out-degree constraints of satellite nodes during data routing

[0030]

[0031] And the in-degree and out-degree constraints of satellite nodes during data routing

[0032]

[0033] Among them, y w,v is whether the content w is deployed on the satellite node v, is whether user u accesses content w through satellite node v, x u,w Whether user u accesses content w, a u,dc is whether user u accesses content from the ground data center through the satellite network, U is the user task set, W is the accessible content set, and s w is the task w, w∈W, the content data size, is the storage resource capacity that satellite node v,v∈V can provide, t u,w is the service delay for user u to access content w, is the maximum service delay for user u to access content w, is the maximum number of accessible users of satellite v, Whether user u uses link e, b in the process of accessing content w u is the actual data rate at which user u accesses content w, B e is the bandwidth resource capacity of the intersatellite link e, e∈E, E is the set of intersatellite links between all satellite nodes, and is the input degree set and output degree set of satellite v, Satellite v is regarded as the access satellite v of the cloud center dc dc,a , V is the set of satellite nodes, v u,a It is the access satellite for the cloud center DC.

[0034] Furthermore, the joint optimization mathematical model includes

[0035]

[0036] The objective function is expressed as the average deployment cost per user, and the cost factors of network bandwidth usage cost and on-orbit storage resource usage cost are expressed as and The user task set is U and the number of users is M.

[0037] Furthermore, in the satellite-ground collaborative caching and resource allocation optimization method, each satellite node exchanges information with adjacent satellites to obtain current storage resources and content deployment information. If the storage resources of the current neighboring satellite node are insufficient, the access volume is limited, or the ground data center is adjacent, the user can directly obtain access content from the ground data center through the intersatellite link, including:

[0038] Each access satellite node obtains the operating status of the neighboring satellite sub-network based on the number of network hops, and obtains feasible strategies for content placement and routing paths by traversing the satellites and links in the neighboring sub-networks. In the initial layer, each user's access satellite is the only root candidate. After searching for the root candidate, the neighboring satellites of the root candidate become the new candidates for the next layer. Regardless of whether the current layer obtains a feasible strategy, it will continue to search for new candidate strategies for the next layer until the current number of hops in the sub-network reaches the maximum.

[0039] Secondly, when the available storage resources in the subnetwork are insufficient, the content service is limited, or the access satellite of the cloud center is within its neighborhood subnetwork, the user's content service can be provided by the cloud center; at this time, the shortest path between the user's access satellite and the cloud center is traversed, and the feasible routing path is obtained based on descending order; in this case, the feasible strategy with the minimum deployment cost will be considered as the strategy for the collaborative caching and resource allocation problem, including resource allocation, content caching, and access.

[0040] A satellite-ground integrated network resource management and content collaborative caching system, comprising:

[0041] The user end located in the multi-dimensional space of land, sea and air sends a request service information to the server located in the satellite edge cloud and the central cloud to obtain the required content data in real time;

[0042] The operation control center located on the ground can perform integrated management and control of the satellite edge cloud and the ground center cloud based on the satellite-ground cross-domain network. By real-time monitoring of the operation status of the satellite network and the ground center cloud and the current task execution status, the operation control center can independently complete task scheduling and resource allocation according to the current access user request and network status, and share with the satellite edge cloud and the ground center cloud through information interaction to complete resource configuration, task deployment and execution;

[0043] The satellite edge cloud module is used for each satellite node to interconnect with four adjacent satellite nodes through inter-satellite links, and form a satellite neighborhood sub-network with adjacent satellite nodes based on the number of network hops; satellite nodes in the satellite network provide users with on-orbit storage services by carrying a certain storage payload, and provide users with content storage services on demand; satellite nodes send the operating status of each node and the task execution status to the operation control center through inter-satellite and satellite-to-ground links according to time slots. The operation control center monitors the operating status of the satellite edge cloud in real time and uniformly arranges available resources;

[0044] The ground-based central cloud module is located far away from the user end and is used to collaborate with the satellite edge cloud module to provide users with storage resources and content caching services.

[0045] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a satellite-ground fusion network resource management and content collaborative caching method are implemented.

[0046] A satellite-ground fusion network resource management and content collaborative caching device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the satellite-ground fusion network resource management and content collaborative caching method are implemented.

[0047] The advantages of the present invention compared with the prior art are:

[0048] (1) Ground-based master control + satellite-based auxiliary control satellite-ground fusion network resource management architecture. In order to solve the problems of low utilization of satellite-ground cross-domain network resources, poor system compatibility, and insufficient real-time decision-making, a ground-based master control + satellite-based auxiliary control satellite-ground fusion network resource management system architecture is established. The ground-based master control can realize dynamic management of the entire domain resources of the satellite-ground fusion network. The satellite nodes have certain autonomous capabilities and can realize real-time monitoring of the operating status of the domain sub-network and autonomous content access. Based on user service needs and on-orbit cache content, users can quickly obtain cache content through inter-satellite collaboration, or access ground cloud data through inter-satellite links, realizing satellite-ground network resource integration, on-demand management, and timely service supply;

[0049] (2) Based on the mathematical model of satellite-ground collaborative caching and resource optimization, a generalized satellite-ground collaborative caching and resource optimization mathematical model under multi-physical constraints was established to meet the needs of satellite Internet application services. This model can jointly reduce the cost of on-orbit cache resources and satellite network bandwidth resources, and effectively improve the operating efficiency of the satellite-ground integrated network and user service experience. This mathematical model can realize a variety of problem model variants through customized design methods, such as cache resource optimization, network bandwidth resource optimization, service time minimization, etc.

[0050] (3) Collaborative caching and resource optimization method based on neighborhood search Considering that the proposed problem is NP-hard and solving the optimal strategy has high computational complexity, a collaborative caching and resource optimization method based on neighborhood search is proposed. The access satellite can autonomously manage its neighborhood sub-network, allocate cache resources and deploy cache content within the sub-network, and quickly obtain the current resource allocation, content cache location, routing selection strategy, etc. by traversing the sub-network nodes. The neighborhood search method can effectively reduce the size of the current solution space, quickly realize collaborative caching and resource optimization strategy selection, and can be applied to large-scale satellite-ground fusion network application needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0052] Figure 1 This is a schematic diagram of the architecture of the satellite-ground integrated network resource management system;

[0053] Figure 2 This is a schematic diagram of the satellite-ground collaborative content access model;

[0054] Figure 3 This is a schematic diagram of the satellite-ground collaborative caching and resource optimization method;

[0055] Figure 4 The collaborative caching and resource allocation results in three different application scenarios, where (a) is the storage cost, (b) is the bandwidth cost, and (c) is the total deployment cost;

[0056] Figure 5 The collaborative caching and resource optimization results of three different algorithms, where (a) is the storage cost, (b) is the bandwidth cost, and (c) is the total deployment cost. DETAILED DESCRIPTION

[0057] In order to better understand the above technical scheme, the technical scheme of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical scheme of the present invention, rather than limitations on the technical scheme of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0058] The following is a further detailed description of a satellite-ground integrated network resource management and content collaborative caching method and system provided by an embodiment of the present invention in conjunction with the accompanying drawings. The specific implementation method may include:

[0059] (1) Each satellite node obtains the random access request information of the user end in the current time slot in real time;

[0060] (2) According to the time slot network model, in each time slot, the network autonomously perceives status information including network topology, task operation status, resource usage, and task service requirements;

[0061] (3) Based on the acquired network status and user access request information, the ground operation and control center establishes a satellite-ground integrated network resource management and content collaborative access system model, and constructs a joint optimization mathematical model for network storage resources and network bandwidth resources under multiple physical constraints;

[0062] (4) The ground operation and control center uses satellite-ground collaborative caching and resource configuration optimization methods to complete satellite-ground collaborative caching, resource optimization configuration, and cache content access strategy selection to minimize the satellite-ground network deployment cost;

[0063] (5) The satellite-ground fusion network implements resource allocation and content cache deployment according to the optimization strategy obtained in step (4), and provides cache content collaborative access services for the user end.

[0064] Furthermore, in step (1), each satellite can only establish a satellite-to-ground link with a user terminal within its coverage area and provide network access services for the user terminal.

[0065] In one possible implementation, in step (2), the satellite-ground fusion network can autonomously obtain the network's operating status according to the time slot, including the current location, resource usage, cache content type, etc.

[0066] Optionally, in a possible implementation method, in step (3), a satellite-ground integrated network resource management and content collaborative access system model and a joint optimization mathematical model are established. When a user accesses content in the satellite edge cloud, a certain network bandwidth usage cost is generated, where the bandwidth usage cost of user u during content access is expressed as:

[0067]

[0068] Among them, x u,w = {0,1} indicates whether user u accesses content w, where x u,w =1 indicates that user u is accessing content w, otherwise x u,w =0. Indicates whether user u uses link e in the process of accessing content w, where indicates that user u used link e in the process of accessing content w, otherwise The actual data rate at which user u retrieves content w is denoted as b u , E is the set of intersatellite links between all satellite nodes;

[0069] When accessing content, it takes up a certain amount of storage resources when deployed on satellite nodes. When different user tasks access the same content, the content can be deployed on a satellite node, thereby effectively reducing the number of storage resources used. For user u, if the current content is deployed when it is first accessed, the storage resources of the content need to be considered. If the current content is not deployed when it is accessed for the first time, the storage resources of the content do not need to be considered. That is, the storage resources generated when user u accesses the content at the current moment can be expressed as:

[0070]

[0071] Among them, a u,dc = {0,1} indicates whether user u accesses content from the ground data center via the satellite network, a u,dc =1 means accessing content from the ground data center via the satellite network, otherwise a u,dc =0. w,v = {0,1} indicates whether content w is deployed on satellite node v, where y w,v =1 means content w is deployed on satellite node v, otherwise y w,v =0. Indicates whether user u accesses content w through satellite node v, where Indicates that user u accesses content w, otherwise Content w data size representation s w , W is the accessible content set.

[0072] In one possible implementation, from the perspective of user service experience and satellite network operation utility, taking into account the overall interests of user tasks and satellite networks, an optimization objective function of network bandwidth usage cost and on-orbit storage resource usage cost is established based on the weighted sum method. The joint optimization objective function can be expressed as:

[0073]

[0074] The objective function is expressed as the average deployment cost per user, and the cost factors of network bandwidth usage cost and on-orbit storage resource usage cost are expressed as and The user task set is U and the number of users is M.

[0075] Preferably, in step (3), various physical constraints such as satellite node resources, link bandwidth resources, and task deployment need to be met in the satellite-ground collaborative caching and content access mathematical model.

[0076] When user u accesses content via satellite, each user accesses the current content at a satellite node. Considering that the accessed content can be deployed on multiple satellite nodes at the same time, the user access constraint can be specifically expressed as:

[0077]

[0078] Since satellite node resources are limited, the currently available resources must not be less than the resources required by the access task. The storage resource constraints of satellite nodes when accessing content cache can be expressed as:

[0079]

[0080] Among them, the storage resource capacity that the satellite node v,v∈V can provide is expressed as

[0081] The content w of each user u is served with a delay t u,w Not exceeding the maximum acceptable service delay It can be expressed as:

[0082]

[0083] Furthermore, the number of access contents of each satellite node is limited, and the maximum number of access users of satellite v is expressed as When , the access service constraints provided by each satellite node to the user are expressed as:

[0084]

[0085] If the access satellite node resources are insufficient, the user needs to access the content through links to other satellite nodes, that is, it is necessary to ensure that the bandwidth resources required by the intersatellite link e when routing data is not greater than the currently available bandwidth resources B e , then the bandwidth resource constraint is expressed as:

[0086]

[0087] When users access content through the satellite edge cloud, the data input and output of each satellite node except the satellite node storing the content and the access satellite node must be consistent during the satellite network routing process. and is the input degree set and output degree set of satellite v. The in-degree and out-degree constraints of satellite nodes during data routing can be expressed as:

[0088]

[0089] In addition, in general, it is necessary to ensure that the input and output degrees of the satellite are equal. Indicates that satellite v is regarded as the access satellite v of cloud center dc dc,a ,otherwise Then the path selection constraints of user u and content w can be:

[0090]

[0091] Preferably, in step (4), in the satellite-ground integrated network resource management and content collaborative access optimization method, each satellite node exchanges information with an adjacent satellite to obtain current storage resources and content deployment information. If the storage resources of the current neighboring satellite node are insufficient, the access volume is limited, or the ground data center is adjacent, the user can directly obtain access content from the ground data center through the intersatellite link. The specific process is as follows:

[0092] First, each access satellite node obtains the operating status of the neighboring satellite sub-network based on the number of network hops, and obtains feasible strategies for content placement and routing paths by traversing the satellites and links in the neighboring sub-network. In the initial layer, each user's access satellite is the only root candidate. After searching for the root candidate, the neighboring satellites of the root candidate become new candidates for the next layer. In order to obtain a feasible strategy with the minimum deployment cost, regardless of whether the current layer obtains a feasible strategy, the search for new candidate strategies for the next layer will continue until the current number of hops in the sub-network reaches the maximum.

[0093] Secondly, when the available storage resources in the subnetwork are insufficient, the content service is limited, or the access satellite of the cloud center is in its neighborhood subnetwork, the user's content service can be provided by the cloud center. At this time, the shortest path between the user's access satellite and the cloud center can be traversed to obtain the feasible routing path in descending order. In this case, the feasible strategy with the minimum deployment cost will be considered as the strategy for the collaborative caching and resource allocation problem, including resource allocation, content caching, and service provision.

[0094] Preferably, in step (5), resource configuration, cache deployment and content access services are implemented based on the optimization strategy obtained in step (4).

[0095] In a second aspect, an embodiment of the present invention provides a satellite-ground integrated network resource management and content collaborative caching system, including:

[0096] (1) The user end located in the multi-dimensional space of land, sea and air sends a request service information to the server located in the satellite edge cloud and the central cloud, and obtains the required content data in real time.

[0097] (2) The ground-based operation control center can integrate the satellite edge cloud and the ground center cloud based on the satellite-ground cross-domain network. It can monitor the operation status of the satellite network and the ground center cloud network and the current task execution status in real time, and independently complete task scheduling and resource allocation according to the current access user requests and network status. It can share information with the satellite edge cloud and the ground center cloud through information interaction to complete resource configuration, task deployment and execution.

[0098] (3) Each satellite node of the satellite edge cloud is interconnected with four adjacent satellite nodes through inter-satellite links. Each satellite node forms a satellite neighborhood sub-network with adjacent satellite nodes based on the number of network hops. Satellite nodes in the satellite network provide users with on-orbit storage services by carrying a certain storage payload. By building a satellite edge cloud, flexible management and efficient use of on-orbit resources are achieved, providing users with content storage services on demand. Satellite nodes send the operating status and task execution status of each node to the operation and control center through inter-satellite / satellite-to-ground links according to time slots. The operation and control center is responsible for real-time monitoring of the operating status of the satellite edge cloud and unified arrangement of available resources.

[0099] (4) Unlike the strictly limited storage resources in the ground central cloud and the satellite edge cloud, the ground central cloud is located far away from the user end but has sufficient storage and other resources, and can collaborate with the satellite edge cloud to provide content caching services to users.

[0100] In the solution provided in the embodiment of the present invention, a method is first constructed to meet the satellite-ground collaborative cache service application requirements of satellite Internet. Figure 1 The satellite-ground integrated network resource management system architecture of ground main control + onboard auxiliary control shown in the figure includes the user terminal located in multi-dimensional space, the satellite edge cloud, the operation control center located on the ground, and the ground central cloud.

[0101] (1) The user end located in the multi-dimensional space of land, sea and air sends a request service information to the server located in the satellite edge cloud and the central cloud, and obtains the required content data in real time.

[0102] (2) The ground-based operation control center can integrate the satellite edge cloud and the ground center cloud based on the satellite-ground cross-domain network. By real-time monitoring of the operating status of the satellite network and the ground center cloud network and the current task execution status, it can dynamically manage network resources in a centralized manner, and autonomously complete task scheduling and resource allocation based on current access user requests and network status. It can also share information with the satellite edge cloud and the ground center cloud through information interaction to complete resource configuration, task deployment and execution.

[0103] (3) Satellite edge cloud Satellite nodes in the satellite network provide users with on-orbit storage services by carrying a certain storage payload. By building a satellite edge cloud, flexible management and efficient use of on-orbit resources are achieved, providing users with content storage services on demand. Satellite nodes send the operating status of each node and the task execution status to the operation control center through inter-satellite / satellite-to-ground links according to time slots. The operation control center is responsible for real-time monitoring of the operating status of the satellite edge cloud and unified arrangement of available resources.

[0104] (4) Unlike the ground-based central cloud and the satellite edge cloud, which have strictly limited storage resources, the ground-based central cloud is located far away from the user end but has sufficient storage and other resources, and can collaborate with the satellite edge cloud to provide content caching services to users.

[0105] Aiming at the complex environment of satellite network with dynamic and time-varying topology and random access of user tasks, a satellite network and user task model based on quasi-static scenario is established with reference to the related work of existing satellite networks. The satellite network topology remains unchanged within a time slot and changes dynamically in different time slots. The user tasks remain unchanged during the operation cycle and their service requirements can be met. Assuming that a batch of user tasks arrive at the satellite node at the same time at the beginning of each time slot, the satellite node provides content access services on demand for the currently connected user tasks according to the predefined content cache and access strategy.

[0106] When accessing content through satellite-ground collaboration, the user task first sends the access request information to the satellite edge cloud through the currently accessed satellite node. The satellite edge cloud synchronizes the current network and content storage status through information sharing, and autonomously obtains content access requests. The satellite-ground collaborative caching and content access process can be divided into two stages: content collaborative caching and cache content collaborative access. In the content collaborative caching process, the satellite edge cloud implements content caching and access strategy selection based on the current edge cloud network status and user access requests, and completes cache content deployment through satellite-ground resource optimization methods. In the cache content access process, content access services are provided to users based on the deployed content data in stage one. It should be noted that in order to effectively utilize satellite-ground cross-domain resources, the satellite-ground collaborative caching and content access stages use a joint optimization method to calculate their final strategies. The access satellite and several adjacent satellite nodes can provide users with content access services, or directly access the ground data center through inter-satellite links. The specific steps are as follows:

[0107] (1) Each satellite node obtains the random access request information of the user end in the current time slot in real time;

[0108] (2) According to the time slot network model, in each time slot, the network autonomously perceives status information including network topology, task operation status, resource usage, and task service requirements;

[0109] (3) Based on the acquired network status and user access request information, the ground operation and control center establishes a satellite-ground integrated network resource management and content collaborative access system model, and constructs a joint optimization mathematical model for network storage resources and network bandwidth resources under multiple physical constraints;

[0110] In order to better explain the integrated network resource management and content collaborative cache access method, the present invention establishes the following system model in combination with the embodiments.

[0111] The satellite network is represented as a directed graph G(V,E), where V represents a set of N satellite nodes and E represents a set of intersatellite links between all satellite nodes, based on a central satellite and the number of network hops h. The storage resources supported by the satellite node are represented as mem. The resource capacity that a satellite node v, v∈V can provide is represented as There are four intersatellite links between each satellite node and its adjacent satellite nodes, two of which are from the same orbital plane, and the other two are from adjacent orbital planes. The bandwidth resource capacity of the intersatellite link e,e∈E, is denoted as B e Considering the limited available resources of satellites, each satellite can only provide content services to multiple users, where the maximum number of users accessing satellite v can be expressed as The input degree set and output degree set of satellite v can be expressed as and In addition, the cloud center DC has sufficient available storage and satellite-to-ground bandwidth resources, and the cloud center is also connected to the satellite v dc,a within the coverage area.

[0112] In the satellite-ground collaborative access application scenario, users come from sensors and terminal devices located in multi-dimensional spaces such as the sky, the earth, the sea, etc., where the user task set is U and the number of users is M. Considering that in remote areas lacking ground networks, satellite nodes can only establish access links and communicate with users in their coverage areas. Users not covered by satellites cannot offload computing tasks to the satellite edge cloud through satellite nodes. All users are randomly located in different satellite node coverage areas and obtain the current access content by communicating with satellite nodes. Specifically, when satellite v provides content services for user u, the access satellite will be represented as access satellite v. u,a The actual data rate at which user u retrieves content w is represented by b u .

[0113] The set of accessed content is W, which includes Q content. For each content w, w∈W, the data size and hotspot degree are represented by s w and p w Each user task randomly selects access content according to the current content's hotness. The more hot content is, the more likely it is to be accessed by the user. When the user accesses content, the user terminal needs to exchange information with the satellite node through the satellite-to-ground link. When the user accesses the satellite node and the current satellite node has insufficient available resources, content access needs to be achieved through multi-node collaborative caching. Assuming that the maximum delay for user u to access content w, w∈W, is expressed as

[0114] Reference for satellite-ground collaborative caching and content access model Figure 2 As shown, the satellite edge content access process includes 9 users. Each satellite node is deployed with a storage server and has a certain coverage area. The satellite node can directly exchange information with users in its coverage area through the satellite-to-ground link, and determine the current satellite-to-ground collaborative cache and user task content access strategy based on the received user task information and the current operating status of the satellite network. Specifically, based on the sufficient available resources of the current satellite node, user 1 directly obtains content data by accessing satellite 1, and user 2 obtains content data from satellite 1 by accessing satellite 4. In case the cache resources of the current satellite node are insufficient, user 3 obtains content data from satellite 3 through satellite 2, and user 7 obtains content data from the ground data center through the intersatellite link between satellite 6 and satellite 5. For users who are not in the coverage area of ​​the current satellite, they cannot obtain content access services through the satellite edge cloud.

[0115] During the user content access process, different caching and access strategies have different impacts on the overall operational performance of the satellite network and the user service experience. For user terminals, the user content access process requires a certain execution delay. Satellite nodes need to incur certain bandwidth costs and storage costs during content caching and data distribution. The present invention takes into account both the user service experience and the overall performance of the satellite network during the satellite-ground collaborative caching and content access process, establishes a joint minimization mathematical problem of network bandwidth usage and inter-satellite storage resource usage under the constraints of cache content deployment, collaborative access, physical resource configuration, and other conditions, and optimizes the average total deployment cost objective function per user.

[0116] The present invention establishes the following mathematical model in combination with the embodiments.

[0117] In order to better abstract and express the mathematical problem of the above-mentioned satellite-ground collaborative caching, the following binary decision variables and intermediate variables are first defined.

[0118] Binary decision variable x u,w = {0,1} indicates whether user u accesses content w, where x u,w =1 indicates that user u is accessing content w, otherwise x u,w =0.

[0119] Binary decision variable y w,v = {0,1} indicates whether content w is deployed on satellite node v, where y w,v =1 means content w is deployed on satellite node v, otherwise y w,v =0.

[0120] Binary decision variables Indicates whether user u accesses content w through satellite node v, where Indicates that user u accesses content w, otherwise

[0121] Binary decision variables Indicates whether user u uses link e in the process of accessing content w, where indicates that user u used link e in the process of accessing content w, otherwise

[0122] Binary decision variable a u,dc = {0,1} indicates whether user u accesses content from the ground data center via the satellite network, where a u,dc =1 means accessing content from the ground data center via the satellite network, otherwise a u,dc =0.

[0123] When a user accesses content in the satellite edge cloud, a certain network bandwidth usage cost is incurred, where the bandwidth usage cost of user u during content access can be expressed as:

[0124]

[0125] In addition, accessing content requires certain storage resources when deployed on satellite nodes. When different user tasks access the same content, the content can be deployed on one satellite node, thereby effectively reducing the number of storage resources used. For user u, if the current content is deployed when it is first accessed, the storage resources of the content need to be considered. If the current content is not deployed when it is accessed for the first time, the storage resources of the content do not need to be considered. That is, the storage resources generated when user u accesses the content at the current moment can be expressed as:

[0126]

[0127] From the perspectives of user service experience and satellite network operation utility, taking into account the overall interests of user tasks and satellite networks, an optimization objective function of network bandwidth usage cost and on-orbit storage resource usage cost is established based on the weighted sum method, where the objective function is expressed as the average deployment cost per user. Assume that the cost factors of network bandwidth usage cost and on-orbit storage resource usage cost are expressed as and When users access content, the joint optimization objective function can be expressed as:

[0128]

[0129] In the process of satellite-ground collaborative caching and content access, various physical constraints such as satellite node resources, link bandwidth resources, and task deployment need to be met. The specific constraints are described as follows.

[0130] When user u accesses content through the satellite edge cloud, each user accesses the current content at a satellite node. Considering that the accessed content can be deployed on multiple satellite nodes at the same time, the user access constraint can be specifically expressed as:

[0131]

[0132] Since satellite node resources are limited, the currently available resources must not be less than the resources required by the access task. The storage resource constraints of satellite nodes when accessing content cache can be expressed as:

[0133]

[0134] At the same time, it is ensured that the content service delay of each user does not exceed the maximum acceptable service delay, which can be expressed as:

[0135]

[0136] Furthermore, considering that each satellite node has a limited number of access contents, the access service constraints provided by each satellite node to the user can be expressed as:

[0137]

[0138] If the access satellite node resources are insufficient, the user needs to access the content through links to other satellite nodes, that is, it is necessary to ensure that the bandwidth resources required by the intersatellite link used to route data is not greater than the currently available bandwidth resources. The bandwidth resource constraint condition can be expressed as:

[0139]

[0140] When users access content through the satellite edge cloud, the access data must be routed through the satellite network to ensure that the data input and output of each satellite node, except for the satellite node storing the content and the access satellite node, are consistent. That is, the in-degree and out-degree constraints of the satellite node during data routing can be expressed as:

[0141]

[0142] In addition, it is guaranteed that the input and output degrees of each satellite are always equal. Indicates that satellite v is regarded as the access satellite v of cloud center dc dc,a ,otherwise Then the path selection constraints of user u and content w can be:

[0143]

[0144] (4) The ground operation and control center uses satellite-ground collaborative caching and resource configuration optimization methods to complete satellite-ground collaborative caching, resource optimization configuration, and cache content access strategy selection to minimize the satellite-ground network deployment cost;

[0145] Considering that the constructed problem model belongs to an NP-hard problem, in order to reduce the computational complexity of solving the problem model, the present invention first divides the satellite network into several interdependent sub-networks, and performs caching strategy, content deployment and user access process execution on the access content based on the satellite-ground collaborative caching and resource optimization method.

[0146] Taking into account the huge network state synchronization overhead, high control complexity and poor decision-making real-time performance when large-scale satellite constellations manage and schedule storage, link and bandwidth resources in a global manner, each satellite node in the present invention can only interact with adjacent satellites to obtain current storage resources and content deployment. If the storage resources of the current neighborhood satellite nodes are insufficient, the access volume is limited or the ground data center is nearby, the user can directly obtain access content from the ground data center through the inter-satellite link, assuming that the storage resources of the ground data center are sufficient and the user access volume is not restricted.

[0147] When a user requests random access to the satellite edge cloud, the satellite node first autonomously updates and obtains the available storage resources and deployed access content of the current adjacent satellite nodes, and selects the best content deployment and access strategy for the user based on the current network operation status. It should be noted that considering that multiple users may currently access the same content, the access content data can be shared by multiple users, which can effectively reduce the cost of using on-orbit storage resources. In addition, obtaining access content from neighboring nodes close to the access satellite as much as possible can effectively reduce network bandwidth usage.

[0148] For satellite networks, we can first calculate the number of hops h sub A neighboring subnetwork is established for each satellite v, and each satellite is regarded as an intelligent agent with environmental perception, autonomy and social behavior, which is responsible for resource management, content caching and access services in the neighboring subnetwork. Due to the limited onboard storage resources, different satellites in the subnetwork can provide users with collaborative caching services through inter-satellite links to improve user service experience and network operation utility. When the available storage resources in the subnetwork are insufficient or the service provision is limited, users will obtain the required content from the cloud center in a collaborative manner through the satellite network.

[0149] In addition, the utilization rate of onboard storage resources is improved through content sharing technology, that is, different users with the same service requirements can access the same content deployed on the satellite. Considering that cached content with higher popularity is more easily accessible to users, all accessing users of each satellite can be sorted from high to low according to the popularity of the content, and user collaborative caching and resource allocation strategies can be formulated, deployed and executed one by one.

[0150] Specifically, for each user's content service, a neighborhood search method is used to obtain feasible strategies for content placement and routing paths by traversing satellites and links in neighboring subnetworks. In the initial layer, each user's access satellite is regarded as the only root candidate. If the required content has been deployed or the available storage resources are sufficient to cache the content, the root candidate is first searched to obtain a feasible strategy. After the root candidate is searched, the neighboring satellites of the root candidate will become new candidates for the next layer. It should be noted that a satellite in the subnetwork that has the required content may provide content services to the user, then the storage resource usage of the user's content service can be regarded as 0. Therefore, in order to obtain a feasible strategy with the minimum deployment cost, regardless of whether the current layer obtains a feasible strategy, the search for new candidate strategies in the next layer will continue until the current number of hops in the subnetwork is the largest.

[0151] When the available storage resources in the subnetwork are insufficient, the content service is limited, or the access satellite of the cloud center is in its neighborhood subnetwork, the user's content service can be provided by the cloud center. At this time, the L shortest paths between the access satellite of user u and the cloud center dc can be traversed The feasible routing paths are obtained in descending order. In this case, the feasible strategy with the minimum deployment cost will be considered as the strategy for the collaborative caching and resource allocation problem, including resource allocation, content caching, and service provision.

[0152] To further describe the operation process of the proposed method, refer to Figure 3 First, establish the satellite v0 in h sub =1 and h sub = 2, represented by green and red lines, respectively. Then, the neighborhood search method is used to obtain the feasible strategy h for collaborative caching and resource allocation of content services in the neighboring subnetwork with the minimum deployment cost. sub =2. Specifically, for a user, first search for the root candidate of the initial layer, that is, access satellite v0, but due to insufficient storage resources, no feasible content service strategy can be provided. Then, traverse the candidate satellites of the next layer {v1, v2, v3, v4}, and obtain two feasible strategies, namely strategy 1 and strategy 2. For strategy 1, satellite v1 has sufficient storage resources to deploy the required content, and the content can be deployed through the routing path v1→v0. For strategy 2, since the required content is deployed on satellite v4, it only needs to go through the routing path v4→v0, and the deployment cost can only come from network bandwidth consumption. In addition, continue to search the candidate solutions of the third layer {v5, v6,…, v 12}, and get strategy 3, in which the required content is also deployed on satellite v8, and content services can be provided through the routing path v8→v3→v0. Therefore, considering that the network consumption of strategy 3 is greater than that of strategy 2, strategy 2 will be better than strategy 1 and strategy 3, and will be regarded as the feasible strategy with the lowest deployment cost.

[0153] In a dynamic environment, the operation control center autonomously perceives changes in the surrounding environment by collecting information such as business needs and network operation status in each time slot, and then formulates collaborative caching and resource allocation strategies for new users one by one. When the time when the user has not accessed the content exceeds the maximum threshold time, the cached content on the satellite will be released to reduce the use of storage resources. However, in actual application scenarios, considering the real-time nature of user content services, the user's content service can be provided based on the content caching strategy generated in the previous time slot, and then the performance of collaborative caching and resource allocation can be improved based on the user's current service needs.

[0154] The present invention performs a performance analysis on the above-mentioned method based on a network simulation application scenario.

[0155] Based on the STK software, the orbital parameters of the existing Iridium II satellite constellation were obtained, and a Walker constellation with 66 LEO satellites was established. There are 6 orbital planes in total, each of which includes 11 LEO satellites with an orbital altitude of 780km. Each satellite has a storage resource of 1000Mbits, the maximum number of user missions that can be accessed is 30, and the bandwidth resource of the inter-satellite link is 100Mbps. The 5th satellite in the 4th orbit is used as the access satellite node to establish a satellite sub-network with a network hop count of 2. The ground data center is located within the coverage of the 5th satellite in the 6th orbit. The available storage resources in the cloud center and the available bandwidth resources between the cloud and the access satellite are considered sufficient. The number of paths between the cloud center and the access satellite is indicated as 4. In addition, the hop count of each adjacent sub-network is considered to be 1.

[0156] In addition, it is assumed that users can be randomly deployed within the satellite coverage. For each content, the data size and content popularity can be generated from [100,500]Mbits and [1,10] respectively. Assuming that the service delay for each user to obtain the content is less than the maximum service delay, the storage resource usage cost coefficient and the network bandwidth consumption cost coefficient are 0.4 and 0.6 respectively.

[0157] Under the conditions that the number of currently connected satellites is 4, Q = 5 and M = {200, 210, ..., 300}, the experiment analyzes the content service performance in three different scenarios: collaborative caching, edge caching and cloud center. Figure 4 shown.

[0158] The average storage cost of each user service in the three scenarios is as follows: Figure 4As shown in (a). For the cloud center, all content services of the user are provided by the cloud center, and the satellite network without edge cache is only responsible for data routing. For edge cache, considering that the user's content service is only provided by the satellite network with edge cache, as the amount of content deployed on the satellite increases, more content services can be provided to the user. In addition, for collaborative cache, the user's collaborative content service can be provided by the satellite-ground collaborative network. Considering the limited supply of edge services and limited storage resources, the ground cloud center can provide content services to users through the satellite network. Therefore, the average storage cost of each user service of edge cache is higher than that of collaborative cache. Compared with edge cache, the average storage cost of each user service of collaborative cache can be reduced by 30.37%.

[0159] The average bandwidth cost of each user service in the three scenarios is shown in the figure above. Figure 4 (b) shows that the average bandwidth cost of the cloud center is the largest, followed by the collaborative cache and then the edge cache. This is because the cloud center can provide content services for all users of the cloud center and several users of the collaborative cache, while other users of the collaborative cache and all users of the edge cache will be provided with content services by the satellite network of the edge cache. It should be noted that compared with edge-based content services, cloud-based content services will lead to an increase in network bandwidth consumption. On average, the bandwidth cost of each user service of the collaborative cache can be reduced by 83.9% in the case of the cloud center, while it only increases by 32.36% in the case of the edge cache.

[0160] also, Figure 4 (c) provides the average total deployment cost of each user service, where the total deployment cost consists of storage resource usage and network bandwidth consumption based on the weighted sum method. It can be found that the three schemes have different impacts on storage cost and bandwidth cost. However, the total deployment cost of each user service of collaborative caching is lower than that of cloud center and edge caching, and the total deployment cost of each user service of edge caching is also lower than that of cloud center. Compared with cloud center and edge caching, the average total deployment cost of each user service of collaborative caching is reduced by 56.3% and 15.79%, respectively, which also shows that collaborative caching is superior to cloud center and edge caching in reducing total deployment cost.

[0161] Furthermore, the performance comparison of the proposed method with two baseline algorithms, Greedy and BFS, in content services is experimentally analyzed. For the Greedy algorithm, the joint strategy of collaborative caching and resource allocation for the proposed problem can be obtained by greedily searching the adjacent subnetworks until the first feasible strategy is found. However, for BFS, the joint strategy of collaborative caching and resource allocation is based on a multi-priority BFS search, in which all candidate strategies in one search layer are sorted from high to low according to content caching, storage resource occupancy, and service latency. Figure 5 The experimental results of various user services under the proposed method, Greedy and BFS algorithms are provided, including storage cost, bandwidth cost and total deployment cost.

[0162] Figure 5 (a) Describes the average storage cost of each user service for the proposed method, Greedy, and BFS. For the Greedy algorithm, the collaborative caching service for users is provided in a greedy manner, that is, if the content required by a certain user has not been deployed on the traversed satellites, the first available satellite with sufficient storage resources can be used to cache the required content. In this case, the storage cost of each user service will increase. However, for BFS, when traversing the candidate content of a search layer, the content sharing method of the content service will be given priority to improve the utilization of the onboard storage resources, so as to obtain the strategy of collaborative caching and resource allocation to minimize the storage cost. In addition, for the proposed method, when providing content services to users, the content sharing method of all satellites in the neighboring subnetwork can be given priority. Therefore, the average storage cost of each user service is the largest for Greedy, followed by BFS, and then the proposed method. It should be noted that as the number of accessing users increases, the content sharing method can provide content services to more users, which will correspondingly reduce the storage cost of each user service. On average, the storage cost per user service of the proposed method is reduced by 25.96% compared with Greedy and 20.61% compared with BFS.

[0163] Figure 5 (b) shows the average bandwidth cost of each user service of the proposed method, Greedy and BFS. It can also be found that the average bandwidth cost of each user service of Greedy and BFS is close to the result of the proposed method. Compared with Greedy and BFS, the bandwidth cost of each user service of the proposed method can be reduced by 3.3% and 2.34% on average.

[0164] also, Figure 5 (c) Describes the average total deployment cost of each user service for the proposed method, Greedy, and BFS. Considering that Greedy can provide content services to users in a greedy manner, it cannot guarantee that as many content services as possible are provided to users through content sharing, which may bring the largest total deployment cost of each user service. For BFS, the content sharing method can give priority to all candidates in a search layer, but it cannot guarantee that all candidates between different search layers can obtain content sharing. Therefore, the average total deployment cost of each user service is lower than that of Greedy. For CCRA, it can be guaranteed that all satellites in adjacent subnetworks give priority to content sharing. Therefore, the average total deployment cost of each user service of the proposed method is lower than that of Greedy and BFS.

[0165] Based on the optimization strategy obtained in step (4), resource configuration, cache deployment and content access services are implemented in the satellite-ground fusion network.

[0166] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes Figure 1 The method described.

[0167] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0168] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0169] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0170] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0171] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0172] The contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. A satellite-ground fusion network resource management and content collaborative caching method, characterized in that: include: Each satellite node in the satellite-ground fusion network obtains the random access request information of the user end in the current time slot in real time; According to the time slot network model of the satellite-ground fusion network, the network status information is sensed and obtained in each time slot; Based on the acquired network status information and random access request information, the ground operation control center establishes a satellite-ground integrated network resource management and content collaborative access system model, and builds a joint optimization mathematical model for network storage resources and network bandwidth resources under multiple physical constraints; According to the satellite-ground fusion network resource management and content collaborative access system model, and the joint optimization mathematical model, the satellite-ground collaborative caching and resource configuration optimization method is used to determine the optimization strategy for completing satellite-ground collaborative caching, resource optimization configuration, and cache content access strategy selection, so as to minimize the satellite-ground network deployment cost; The satellite-ground fusion network implements resource configuration and content cache deployment according to the optimization strategy, and provides cache content collaborative access services for the user end.

2. A satellite-ground fusion network resource management and content collaborative caching method according to claim 1, characterized in that: The satellite node only establishes a satellite-to-ground link with a user terminal within its coverage area and provides network access services for the user terminal.

3. A satellite-ground fusion network resource management and content collaborative caching method according to claim 1, characterized in that: The network status information includes current location, network topology, task running status, resource usage, cache content type and task service requirements.

4. A satellite-ground fusion network resource management and content collaborative caching method according to claim 1, characterized in that: The establishment of a satellite-ground fusion network resource management and content collaborative access system model includes the bandwidth usage cost of user u during content access. And the storage resources generated when user u currently accesses the content Among them, x u,w = {0,1} indicates whether user u accesses content w, where x u,w =1 means user u accesses content w, otherwise x u,w =0; Indicates whether user u uses link e in the process of accessing content w, where indicates that user u used link e in the process of accessing content w, otherwise The actual data rate at which user u accesses content w is denoted as b u ; a u,dc = {0,1} indicates whether user u accesses content from the ground data center via the satellite network, a u,dc =1 means accessing content from the ground data center via the satellite network, otherwise a u,dc =0;y w,v = {0,1} indicates whether content w is deployed on satellite node v, where y w,v =1 means content w is deployed on satellite node v, otherwise y w,v =0; Indicates whether user u accesses content w through satellite node v, where Indicates that user u accesses content w, otherwise Content w data size representation s w .

5. A satellite-ground fusion network resource management and content collaborative caching method according to claim 4, characterized in that: The constraints of the satellite-ground fusion network resource management and content collaborative access system model include user access constraints and the storage resource constraints of satellite nodes when accessing content caches And the content w service delay of each user u does not exceed the maximum acceptable service delay And the access service constraints provided by each satellite node to users And bandwidth resource constraints And the in-degree and out-degree constraints of satellite nodes during data routing And the in-degree and out-degree constraints of satellite nodes during data routing Among them, y w,v is whether the content w is deployed on the satellite node v, is whether user u accesses content w through satellite node v, x u,w Whether user u accesses content w, a u,dc is whether user u accesses content from the ground data center through the satellite network, U is the user task set, W is the accessible content set, and s w is the task w, w∈W, the content data size, is the storage resource capacity that satellite node v,v∈V can provide, t u,w is the service delay for user u to access content w, is the maximum service delay for user u to access content w, is the maximum number of accessible users of satellite v, Whether user u uses link e, b in the process of accessing content w u is the actual data rate at which user u accesses content w, B e is the bandwidth resource capacity of the intersatellite link e, e∈E, E is the set of intersatellite links between all satellite nodes, and is the input degree set and output degree set of satellite v, Satellite v is regarded as the access satellite v of the cloud center dc dc,a , V is the set of satellite nodes, v u,a It is the access satellite for the cloud center DC.

6. A satellite-ground fusion network resource management and content collaborative caching method according to claim 1, characterized in that: The joint optimization mathematical model includes The objective function is expressed as the average deployment cost per user, and the cost factors of network bandwidth usage cost and on-orbit storage resource usage cost are expressed as and The user task set is U, and the number of users is M.

7. A satellite-ground fusion network resource management and content collaborative caching method according to claim 1, characterized in that: In the satellite-ground collaborative caching and resource allocation optimization method, each satellite node exchanges information with adjacent satellites to obtain current storage resources and content deployment information. If the storage resources of the current neighboring satellite node are insufficient, the access volume is limited, or the ground data center is adjacent, the user can directly obtain access content from the ground data center through the intersatellite link, including: Each access satellite node obtains the operating status of the neighboring satellite sub-network based on the number of network hops, and obtains feasible strategies for content placement and routing paths by traversing the satellites and links in the neighboring sub-networks. In the initial layer, each user's access satellite is the only root candidate. After searching for the root candidate, the neighboring satellites of the root candidate become the new candidates for the next layer. Regardless of whether the current layer obtains a feasible strategy, it will continue to search for new candidate strategies for the next layer until the current number of hops in the sub-network reaches the maximum. Secondly, when the available storage resources in the subnetwork are insufficient, the content service is limited, or the access satellite of the cloud center is within its neighborhood subnetwork, the user's content service can be provided by the cloud center; at this time, the shortest path between the user's access satellite and the cloud center is traversed, and the feasible routing path is obtained based on descending order; in this case, the feasible strategy with the minimum deployment cost will be considered as the strategy for the collaborative caching and resource allocation problem, including resource allocation, content caching, and access.

8. A satellite-ground integrated network resource management and content collaborative caching system, characterized in that: include: The user end located in the multi-dimensional space of land, sea and air sends a request service information to the server located in the satellite edge cloud and the central cloud to obtain the required content data in real time; The operation control center located on the ground can perform integrated management and control of the satellite edge cloud and the ground center cloud based on the satellite-ground cross-domain network. By real-time monitoring of the operation status of the satellite network and the ground center cloud and the current task execution status, the operation control center can independently complete task scheduling and resource allocation according to the current access user request and network status, and share with the satellite edge cloud and the ground center cloud through information interaction to complete resource configuration, task deployment and execution; Satellite edge cloud module, used for each satellite node to interconnect with four adjacent satellite nodes through inter-satellite links, and form a satellite neighborhood sub-network with adjacent satellite nodes based on the number of network hops; Satellite nodes in the satellite network provide users with on-orbit storage services by carrying certain storage payloads, as well as content storage services on demand. Satellite nodes send the operating status of each node and the task execution status to the operation control center through inter-satellite and satellite-to-ground links according to time slots. The operation control center monitors the operating status of the satellite edge cloud in real time and uniformly arranges available resources. The ground-based central cloud module is located far away from the user end and is used to collaborate with the satellite edge cloud module to provide users with storage resources and content caching services.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A satellite-ground integrated network resource management and content collaborative caching device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images