Network performance optimization method and device for space-ground integrated Internet

Abstract

The invention provides a network performance optimization method and device for a space-ground integrated internet, and the method comprises the steps: determining a candidate ground station set based on the subscription user historical flow data of the space-ground integrated internet and a predictable satellite-ground connection relation of the space-ground integrated internet; the predictable satellite-ground connection relation is a link relation which can be predicted by the space-ground integrated internet and is formed by a satellite and a ground station; according to a pre-constructed service quality constraint and a pre-constructed cost model, determining a target ground station set to be rented in the candidate ground station set, so that the ground station renting cost of the space-ground integrated internet for network performance optimization based on the target ground station set is minimum; and based on the target ground station set, network performance optimization is carried out on the space-ground integrated internet. The ground station lease cost of network performance optimization of the space-ground integrated internet is minimized on the premise that the network performance requirement of the space-ground integrated internet is met.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated space-ground Internet, and in particular to a network performance optimization method and device for the integrated space-ground Internet. Background Art

[0002] With the rapid development of low-Earth Orbit (LEO) satellite communication technology, the Integrated Satellite-Terrestrial Network (ISTN) is expected to provide global Internet access and low-latency long-distance communication services, and is showing broad application prospects.

[0003] However, due to long construction periods, high costs, and terrain and climate constraints, the early stages of constellation deployment have left a significant imbalance between the widely covered space segment and the scarce ground segment. Consequently, the imbalance in the satellite-ground topology and the disconnected topology between satellite orbits can lead to serious network performance issues.

[0004] Therefore, finding a method to minimize the ground station leasing cost for optimizing the network performance of the space-ground integrated Internet while meeting the network performance requirements of the space-ground integrated Internet has become a current research hotspot. Summary of the Invention

[0005] The present invention provides a network performance optimization method and device for a space-ground integrated Internet, which minimizes the ground station leasing cost for optimizing the network performance of the space-ground integrated Internet while meeting the network performance requirements of the space-ground integrated Internet.

[0006] The present invention provides a network performance optimization method for a space-ground integrated internet. The method comprises: determining a set of candidate ground stations based on historical traffic data of subscribers of the space-ground integrated internet and a predictable satellite-ground connection relationship of the space-ground integrated internet, wherein the set of candidate ground stations has a ground station-as-a-service capability; the predictable satellite-ground connection relationship is a link relationship between satellites and ground stations that is predictable for the space-ground integrated internet; determining a set of target ground stations to be leased from the set of candidate ground stations based on a pre-established quality of service constraint and a pre-established cost model, so as to minimize the ground station leasing cost for network performance optimization of the space-ground integrated internet based on the target ground station set; and performing network performance optimization on the space-ground integrated internet based on the target ground station set.

[0007] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, before determining the target ground station set to be rented in the candidate ground station set based on a pre-built service quality constraint and a pre-built cost model, the method also includes: dividing the continuous time period of the user applying the space-ground integrated Internet into discrete time slices, wherein the discrete time slices include multiple moments; determining the set of traffic demands generated by the user at different moments; determining the target ground station set to be rented in the candidate ground station set based on the pre-built service quality constraint and the pre-built cost model, specifically includes: under the condition that the service quality constraint is satisfied, based on the set of traffic demands generated by the user at different moments, using a pre-built cost model, determining the target ground station set to be rented in the candidate ground station set.

[0008] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, the service quality constraint includes a user service rate constraint; the service quality constraint is pre-constructed in the following manner: determining the number of serviceable user pairs, wherein the number of serviceable user pairs is the number of user pairs to which the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are assigned serviceable ground stations, wherein the serviceable ground stations are ground stations in a set of target ground stations to be rented; determining the number of user pairs for all user pairs; and constructing the user service rate constraint based on the number of serviceable user pairs and the number of user pairs for all user pairs.

[0009] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, the service quality constraint includes a user delay constraint; the service quality constraint is pre-constructed in the following manner: determining the end-to-end delay of a user pair; determining the distribution situation in which the satellite accessed by a source user in the user pair and the satellite accessed by a destination user in the user pair are both assigned serviceable ground stations; and constructing the user delay constraint based on the end-to-end delay of the user pair and the distribution situation in which the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are both assigned serviceable ground stations.

[0010] According to a network performance optimization method for a ground-to-ground integrated Internet provided by the present invention, the cost model is pre-constructed in the following manner: constructing a data transmission cost function between ground stations, and constructing a cost function based on antenna usage time of the ground station; constructing the cost model based on the data transmission cost function between ground stations and the antenna usage time cost function of the ground station.

[0011] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, a data transmission cost function between ground stations is constructed in the following manner: determining the unit price of incoming traffic of ground stations in a set of candidate ground stations, the unit price of outgoing traffic of ground stations in the set of candidate ground stations, and the total amount of traffic generated by user pairs; based on the unit price of incoming traffic, the unit price of outgoing traffic, and the total amount of traffic generated by the user pairs, constructing a data transmission cost function between ground stations.

[0012] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, a cost function based on antenna usage time of a ground station is constructed in the following manner: determining a unit price based on antenna usage time of the ground station and the antenna usage time of the ground station; based on the unit price based on antenna usage time of the ground station and the antenna usage time of the ground station, constructing a cost function based on antenna usage time of the ground station.

[0013] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, before the network performance optimization of the space-ground integrated Internet is performed based on the target ground station set, the method further includes: obtaining the size of the historical traffic of the subscribers of the space-ground integrated Internet, the geographic location of the subscribers and the access satellite pair, and calculating the ground station pair allocated to the subscribers based on the size of the historical traffic of the subscribers, the geographic location of the subscribers and the access satellite pair; based on the ground station pair allocated to the subscribers, statistically obtaining the antenna usage time of the ground station pair allocated to the subscribers; if the antenna usage time does not exceed the time threshold, determining that the ground stations in the target ground station set are leased in an on-demand leasing mode; the network performance optimization of the space-ground integrated Internet based on the target ground station set specifically includes: optimizing the network performance of the space-ground integrated Internet based on the ground stations in the target ground station set that are leased in an on-demand leasing mode.

[0014] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, before the network performance optimization of the space-ground integrated Internet is performed based on the target ground station set, the method further includes: obtaining the size of the historical traffic of the subscribers of the space-ground integrated Internet, the geographic location of the subscribers and the access satellite pair, and calculating the ground station pair allocated to the subscribers based on the size of the historical traffic of the subscribers, the geographic location of the subscribers and the access satellite pair; based on the ground station pair allocated to the subscribers, statistically obtaining the antenna usage time of the ground station pair allocated to the subscribers; when the antenna usage time exceeds a time threshold, determining that the ground stations in the target ground station set are leased in a reserved lease mode; the network performance optimization of the space-ground integrated Internet based on the target ground station set specifically includes: optimizing the network performance of the space-ground integrated Internet based on the ground stations in the target ground station set leased in a reserved lease mode.

[0015] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, the method also includes: for any user pair, calculating a set of available ground station pairs for the user pair, wherein the set of available ground station pairs is a set of candidate ground stations that meets the user delay constraint; aggregating the sets of available ground station pairs for the user pairs in adjacent discrete time slices in chronological order, starting from the first discrete time slice until the last discrete time slice, and obtaining the same available ground stations in the aggregated ground station sets for the user pairs in all discrete time slices based on the aggregation results of the user pairs in all discrete time slices; determining the ground station delay contribution values ​​of the same available ground stations based on the same available ground stations in the aggregated ground station sets for the user pairs in all discrete time slices; using the same available ground station with the largest ground station delay contribution value as the target ground station for the user pair; and determining the target ground station set to be rented based on the target ground stations of each of the user pairs.

[0016] According to a network performance optimization method for a space-ground integrated Internet provided by the present invention, the ground station delay contribution value of the same available ground station is determined in the following manner: determining the reciprocal of the distance from the same available ground station to the center of all other ground station clusters, and the respective weights of all other ground station clusters; based on the reciprocal of the distance from the same available ground station to the center of all other ground station clusters, and the respective weights of all other ground station clusters, determining the ground station delay contribution value of the same available ground station by weighted summation.

[0017] The present invention also provides a network performance optimization device for an integrated space-ground Internet, the device comprising: a determination module for determining a set of candidate ground stations based on historical traffic data of subscribers of the integrated space-ground Internet and a predictable satellite-to-ground connection relationship of the integrated space-ground Internet, wherein the set of candidate ground stations has a ground station-as-a-service capability; the predictable satellite-to-ground connection relationship is a link relationship formed by satellites and ground stations that is predictable for the integrated space-ground Internet; a screening module for determining a set of target ground stations to be rented in the set of candidate ground stations based on pre-constructed service quality constraints and a pre-constructed cost model, so as to minimize the ground station rental cost for network performance optimization of the integrated space-ground Internet based on the target ground station set; and an optimization module for optimizing the network performance of the integrated space-ground Internet based on the target ground station set.

[0018] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements any of the above-described methods for optimizing network performance of the integrated space-ground Internet.

[0019] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for optimizing network performance of the integrated space-ground Internet as described above is implemented.

[0020] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for optimizing network performance of the integrated space-ground Internet.

[0021] The present invention provides a method and device for optimizing the network performance of a space-ground integrated internet. The method includes: determining a set of candidate ground stations based on historical traffic data of subscribers of the space-ground integrated internet and a predictable satellite-to-ground connection relationship of the space-ground integrated internet, wherein the candidate ground station set has a ground station-as-a-service capability; the predictable satellite-to-ground connection relationship is a link relationship formed by satellites and ground stations that is predictable for the space-ground integrated internet; determining a set of target ground stations to be rented from the set of candidate ground stations based on a pre-established quality of service constraint and a pre-established cost model, so as to minimize the ground station rental cost for network performance optimization of the space-ground integrated internet based on the target ground station set; and optimizing the network performance of the space-ground integrated internet based on the target ground station set. This method minimizes the ground station rental cost for network performance optimization of the space-ground integrated internet while meeting the network performance requirements of the space-ground integrated internet. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 It is a grayscale schematic diagram of the framework of the mechanism of the network performance optimization method of the integrated space-ground Internet provided by the present invention.

[0024] Figure 2 It is a color schematic diagram of the framework of the mechanism of the network performance optimization method of the integrated space-ground Internet provided by the present invention.

[0025] Figure 3 This is one of the flow charts of the network performance optimization method of the integrated space-ground Internet provided by the present invention.

[0026] Figure 4 It is a flowchart of determining a target ground station set to be leased from the candidate ground station set according to a pre-built service quality constraint and a pre-built cost model provided by the present invention.

[0027] Figure 5 It is a grayscale schematic diagram of time slice aggregation provided by the present invention.

[0028] Figure 6 It is a color schematic diagram of time slice aggregation provided by the present invention.

[0029] Figure 7 This is the second flow chart of the network performance optimization method of the integrated space-ground Internet provided by the present invention.

[0030] Figure 8 It is a grayscale schematic diagram of the delay contribution value estimation provided by the present invention.

[0031] Figure 9 It is a color schematic diagram of the delay contribution value estimation provided by the present invention.

[0032] Figure 10 It is a structural schematic diagram of the network performance optimization device of the integrated space-ground Internet provided by the present invention.

[0033] Figure 11 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0034] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0035] The network performance optimization method for the integrated space-ground internet, provided in this paper, leverages the emergence of Ground-Station-as-a-Service (GSaaS). This allows integrated space-ground internet operators (also known as ISTN operators) to establish partnerships with ground station service providers, similar to those between traditional terrestrial internet operators. GSaaS allows ISTN operators to lease services such as data computing and transmission on demand, offering significant cost advantages compared to building new ground stations worldwide. Therefore, this paper proposes a network performance optimization method for the integrated space-ground internet, aiming to provide ISTN operators in the early stages of construction with strategies for rationally leasing GSaaS services and corresponding traffic scheduling optimization solutions, thereby minimizing ground station leasing costs while meeting network performance requirements.

[0036] Figure 1 It is a grayscale schematic diagram of the framework of the mechanism of the network performance optimization method of the integrated space-ground Internet provided by the present invention. Figure 2 This is a color schematic diagram of the framework of the mechanism of the network performance optimization method of the integrated space-ground Internet provided by the present invention. It can be understood that Figure 1 and Figure 2 For the same illustration, a grayscale image and a color image are attached for the readability of the present invention.

[0037] in, Figure 1 and Figure 2 The present invention describes its components and functions. Its key concept is that, in the offline phase, the ISTN controller pre-calculates a set of ground station leases based on historical traffic history and predictable satellite-ground station connections, subject to QoS constraints (corresponding to quality of service constraints), and determines the leasing strategy (reservation or on-demand mode) for each station based on a cost model. In the online phase, the controller dynamically dispatches traffic to low-cost and low-latency ground stations. This optimizes the network performance of the integrated space-ground internet based on the target set of ground stations.

[0038] In one embodiment, the present invention can be implemented by a ground-based ISTN controller. During application, the controller, deployed at the ISTN operations center, is responsible not only for selecting leased ground station sites and determining their leasing policies, but also for calculating the selected ground station in real time for each user's traffic flow, ensuring that it meets QoS constraints and maintains low costs. During the offline phase (which can be considered the stage for determining the target ground station set), given that ISTN operators do not need to lease ground stations that their users will never use, the controller first performs time slice aggregation and ground station latency contribution estimation to eliminate redundant ground stations to reduce the ground station combination space. Second, the controller determines the leasing policy for each serviceable ground station, which is influenced by factors such as ground station usage time, user traffic history, and ground station location. During the online phase (which can be considered the stage for optimizing network performance for the integrated ground-ground internet), the controller rapidly responds to schedule each communication flow to the ground station with the lowest leasing cost selected during the offline phase, namely, the operator's own ground station or one leased in a reserved mode. If all leased ground stations cannot meet the QoS requirements or there is no ground station that can serve the new user pair, the controller will immediately calculate new available ground stations from the global candidate ground stations and lease them in a "pay-as-you-go" manner.

[0039] Figure 3 This is one of the flow charts of the network performance optimization method of the integrated space-ground Internet provided by the present invention.

[0040] The following will be combined Figure 3 The process of the network performance optimization method of the integrated space-ground Internet provided by the present invention is described.

[0041] In an exemplary embodiment of the present invention, Figure 3 It can be seen that the network performance optimization method of the integrated space-ground Internet can include steps 310 to 330, and each step will be introduced below.

[0042] In step 310, based on the historical traffic data of subscribers of the integrated space-ground Internet and the predictable satellite-ground connection relationship of the integrated space-ground Internet, a set of candidate ground stations is determined, wherein the candidate ground station set has the ground station as a service capability; the predictable satellite-ground connection relationship is a link relationship between satellites and ground stations that is predictable in the integrated space-ground Internet.

[0043] In another embodiment, the predictable satellite trajectory and satellite-to-ground connection relationship can be used to calculate the ISTN topology for a period of time in the future. Furthermore, the traffic data of its subscribers (corresponding to the historical traffic data of subscribers of the integrated space-ground Internet) can be collected regularly (for example, once a month), including the traffic background and geographical distribution, and the set of ground stations to be rented (corresponding to the candidate ground station set) can be calculated based on this. Among them, the candidate ground stations in the candidate ground station set can be independently operated by different providers and all have the ability to provide GSaaS services, such as data transmission and storage services, and can be interconnected with other ground stations, adjacent cloud servers, or network infrastructure through the ground network.

[0044] In step 320, based on the pre-built service quality constraints and the pre-built cost model, a target ground station set to be leased is determined from the candidate ground station set to minimize the ground station leasing cost for network performance optimization of the integrated space-ground Internet based on the target ground station set.

[0045] In step 330, network performance of the integrated space-ground Internet is optimized based on the target ground station set.

[0046] In one embodiment, a target ground station set to be rented can be determined from a set of candidate ground stations based on pre-established quality of service constraints and a pre-established cost model, so as to minimize the ground station rental cost for the integrated space-ground Internet based on the target ground station set for network performance optimization. Furthermore, the network performance of the integrated space-ground Internet is optimized based on the target ground station set, that is, a low-cost service ground station that meets the delay constraints is allocated to each user flow. If a new user does not have a serviceable ground station, the controller rents a new ground station on demand from the global candidate ground station set and regularly updates the ground station rental strategy. This makes it possible to minimize the ground station rental cost of the integrated space-ground Internet while meeting the network performance requirements of the integrated space-ground Internet.

[0047] Figure 4 It is a flowchart of determining a target ground station set to be leased from the candidate ground station set according to a pre-built service quality constraint and a pre-built cost model provided by the present invention.

[0048] The following will be combined Figure 4 The process of determining a target ground station set to be leased from the candidate ground station set according to a pre-built service quality constraint and a pre-built cost model provided by the present invention is described.

[0049] In an exemplary embodiment of the present invention, Figure 4It can be seen that, according to the pre-built service quality constraints and the pre-built cost model, determining the target ground station set to be leased from the candidate ground station set may include steps 410 to 430, each of which will be described below.

[0050] In step 410, the continuous time period during which the user applies the integrated space-ground Internet is divided into discrete time slices, wherein the discrete time slices include multiple moments.

[0051] In step 420 , a set of traffic demands generated by users at different times is determined.

[0052] In step 430, under the condition that the quality of service constraint is satisfied, based on the user's traffic demand set generated at different times, a target ground station set to be rented is determined from the candidate ground station set through a pre-built cost model.

[0053] It should be noted that an ISTN space segment consists of multiple constellation shells with different orbital altitudes or inclinations, one of which has multiple orbits, and satellites are approximately evenly distributed on each orbit. Since LEO satellites fly dynamically, the present invention divides a continuous time into a set of discrete time slices. , that is, the continuous time period of users using the integrated space-ground Internet is divided into discrete time slices, where a discrete time slice can include multiple moments. At a certain moment, the connection relationship between any two entities in the network (ground station, user and satellite) remains unchanged. At the moment , the entire network can be represented as a graph ,in, is the set of all entities, including satellites , user collection and ground station collection , Represents a set of links. At time The user pair set is represented as ,use As its subscript index. The source and destination users are included in the user collection In addition to the operator's private ground stations (denoted as ), the candidate ground station set is expressed as The controller finally selects the set of serviceable ground stations for leasing as ,in, , , The present invention uses A binary vector of subscript indices as well as right and As a mathematical modeling expression, Elements equal to 1 represent Leased or leaseable.

[0054] The connectivity of network links is represented as There are three types of links: User-Satellite link (USL), Inter-Satellite link (ISL) and Ground-Satellite link (GSL). 0-1 binary variable Indicates the connectivity between any two ISTN entities, which is equal to 1 for nodes There is a connection between them. It is also a binary variable, which is equal to 1 and means arrive There are users on the link of traffic.

[0055] You can make the node The link delay between , then the user The end-to-end delay can be expressed as ,in, .

[0056] At different times, users may generate different traffic sizes. Therefore, the present invention expresses the traffic demand set as ,in, It belongs to the user When traffic is forwarded to a leased ground station, it incurs a transmission cost between ground stations related to its size. That is, during the application process, it is necessary to determine the user's traffic demand set generated at different times.

[0057] The present invention uses Indicates location with satellite A collection of satellites in the same orbit. The service state is replaced by a step function Calculate if , then the function value is 1, otherwise it is 0. Indicates the user's Whether it can be served, a value of 1 indicates that the access satellites of both the source and destination users can be allocated Formally, for a given user pair , whose two access satellites are ,but . Will be assigned from A specific ground station pair selected in .

[0058] In another embodiment, a set of target ground stations to be leased can be determined from a set of candidate ground stations based on a set of user traffic demands generated at different times, while satisfying quality of service constraints. The quality of service constraints can be represented by the user service rate constraint and the user delay constraint described below.

[0059] During the application process, you can use the time slice collection , each user The set of traffic demands generated at different times , and the candidate ground station vector , through the pre-built cost model, we get the ground station pair selected by each user and the final leased ground station vector, that is, we get the candidate ground station set (which can correspond to the candidate ground station vector ) determines the target ground station set to be leased.

[0060] The goal of this invention is to pre-lease some ground stations at a minimum cost within a certain period of time in the future. Based on this result, the traffic of user pairs can be dispatched to specific ground stations that meet the end-to-end delay constraints, and ISTN can ensure high network service rate, that is, to achieve .in, Represents a pre-built cost model.

[0061] In another exemplary embodiment of the present invention, continuing with the above-mentioned embodiment as an example, the service quality constraint may include a user service rate constraint; wherein the service quality constraint may be pre-constructed in the following manner: Determining the number of serviceable user pairs, where the number of serviceable user pairs is the number of user pairs to which both the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are assigned serviceable ground stations, where the serviceable ground stations are ground stations in the set of target ground stations to be leased; Determine the number of user pairs for all user pairs; Based on the number of user pairs that can be served and the number of user pairs of all user pairs, a user service rate constraint is constructed.

[0062] In one embodiment, the user service rate constraint can ensure that the proportion of users with traffic demand and access to ISTN within a time period is at least , that is, at least one ground station can cover the orbital planes of the source and destination access satellites at the same time. The user service rate constraint can be expressed by formula (1): (1) in, Indicates the number of user pairs that can be served (if ); The number of user pairs representing all user pairs.

[0063] The user service rate represents the proportion of time a pair of users are served and is used to measure network reachability under different delay constraints.

[0064] In another exemplary embodiment of the present invention, continuing with the above-mentioned embodiment as an example, the quality of service constraint may include a user delay constraint; wherein the quality of service constraint may be pre-constructed in the following manner: Determine the end-to-end delay for user pairs; Determining that the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are both allocated serviceable ground stations; Based on the end-to-end delay of the user pair and the allocation of serviceable ground stations to the satellites accessed by the source user in the user pair and the satellites accessed by the destination user in the user pair, the user delay constraint is constructed.

[0065] In one embodiment, the user delay constraint guarantees The average end-to-end delay can be The user delay constraint can be expressed by formula (2): (2) in, represents the end-to-end delay of the user pair; It indicates that the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are both allocated serviceable ground stations.

[0066] In another exemplary embodiment of the present invention, continuing with the above-mentioned embodiment as an example, the cost model can be pre-built in the following manner: Constructing a data transmission cost function between ground stations and a cost function based on antenna usage time of ground stations; The cost model is constructed based on a data transmission cost function between ground stations and an antenna usage time cost function of a ground station.

[0067] In one embodiment, the cost function It mainly consists of traffic-related costs and ground station antenna usage time-related costs. The former is defined as the data transmission cost between two ground stations. (corresponding to the data transmission cost function between ground stations). The latter is defined as the cost based on antenna usage time (corresponding to the antenna usage time cost function of the ground station). The cost model can be the sum of the data transmission cost function between ground stations and the antenna usage time cost function of the ground station.

[0068] In another exemplary embodiment of the present invention, the data transmission cost function between ground stations can be constructed in the following manner: determining a unit price of incoming traffic to a ground station in the set of candidate ground stations, a unit price of outgoing traffic to a ground station in the set of candidate ground stations, and a total amount of traffic generated by the user pair; A data transmission cost function between ground stations is constructed based on the incoming traffic unit price, the outgoing traffic unit price, and the total amount of traffic generated by the user pair.

[0069] In one embodiment, the ground station The traffic transmission unit price is divided into the incoming traffic unit price , which is related to the total amount of traffic entering the ground station and the outgoing unit price , which is related to the total amount of traffic transmitted from the ground station. The transmission unit price of ground stations at different sites varies depending on their geographical locations. In the present invention, the transmission unit price of the operator's private ground stations is set to 0. In one example, the transmission cost function (also known as the data transmission cost function between ground stations) can be expressed using formula (3): (3) In another exemplary embodiment of the present invention, the antenna usage time cost function of the ground station can be constructed in the following manner: Determine the unit price of the ground station based on the antenna usage time, and the unit price of the ground station based on the antenna usage time; Based on the antenna usage time-based unit price of the ground station and the antenna usage time-based cost function of the ground station, an antenna usage time-based cost function of the ground station is constructed.

[0070] In one embodiment, there are two charging modes based on the cost of antenna usage time: on-demand and reserved. The unit price based on antenna usage time is defined as , and the usage time is defined as The reservation mode is that the user first prepays a one-time fee for the reserved time. , and then pay for the portion that exceeds the reserved time. The on-demand model is "pay-as-you-go". Its unit price is often higher than the reserved model, but there is no one-time reservation fee. Therefore, the definition of the on-demand model Some are 0. It should be emphasized that the one-time fee of the reservation mode is related to the number of ground stations and often accounts for a large proportion of the total cost.

[0071] In one embodiment, the antenna usage time cost function of the ground station can be expressed as ; Correspondingly, within time The total cost, that is, the cost model can be expressed as formula (4): (4) In another exemplary embodiment of the present invention, the above-described embodiment is continued as an example for description. Before optimizing the network performance of the integrated space-ground Internet based on the target ground station set (corresponding to step 330), the network performance optimization method of the integrated space-ground Internet may further include the following steps: Obtaining a historical traffic size, a geographic location, and an access satellite pair of a subscriber of the integrated space-ground internet, and calculating a ground station pair allocated to the subscriber based on the historical traffic size, the geographic location, and the access satellite pair; Based on the ground station pair allocated to the subscriber, obtaining statistics on antenna usage time of the ground station pair allocated to the subscriber; When the antenna usage time does not exceed the time threshold, the ground stations in the target ground station set are determined to be leased in an on-demand leasing mode; Among them, based on the target ground station set, the network performance optimization of the integrated space-ground Internet can be achieved in the following ways: The ground stations in the target ground station set leased based on the on-demand leasing model are used to optimize the network performance of the integrated space-ground Internet.

[0072] In one embodiment, for each historical user pair, its traffic is pre-scheduled in each time slice to the ground station pair with the lowest estimated transmission cost, and these ground station pairs can meet the delay constraints. Because the present invention requires traversing all user pairs and selecting ground station pairs that can provide continuous service, almost all ground stations that are finally determined to be leased are used at least once within the time period. However, the utilization rate of each ground station varies over time and the duration of use varies. The actual usage time of some ground stations may be shorter than the reserved time. Therefore, for these ground stations, an on-demand leasing model is more economical.

[0073] In one embodiment, in order to determine whether a ground station should be leased in a reservation mode, its size in the context of historical traffic, the user's geographical location, and the access satellite pair can be first obtained, and the ground station pair assigned to each user pair can be calculated, thereby counting the antenna usage time of each ground station (corresponding to the ground station antenna usage time) and comparing it with the time threshold for distinguishing the economic feasibility of the leasing mode; if the threshold is exceeded, the reservation mode is adopted, otherwise the on-demand mode is adopted. That is, the usage time of the historical traffic data of the subscribers of the integrated space-ground Internet is obtained; if the usage time does not exceed the time threshold, it is determined that the ground stations in the target ground station set are leased in an on-demand leasing mode. Furthermore, the network performance of the integrated space-ground Internet can be optimized based on the ground stations in the target ground station set that are leased in an on-demand leasing mode.

[0074] In another exemplary embodiment of the present invention, before performing network performance optimization on the integrated space-ground Internet based on the target ground station set (compare step 330), the network performance optimization method for the integrated space-ground Internet may further include the following steps: Obtaining a historical traffic size, a geographic location, and an access satellite pair of a subscriber of the integrated space-ground internet, and calculating a ground station pair allocated to the subscriber based on the historical traffic size, the geographic location, and the access satellite pair; Based on the ground station pair allocated to the subscriber, obtaining statistics of antenna usage time of the ground station pair allocated to the subscriber; When the antenna usage time exceeds the time threshold, the ground stations in the target ground station set are determined to be leased in a reserved lease mode; The network performance optimization of the integrated space-ground Internet based on the target ground station set can be achieved in the following ways: Optimize network performance of the space-ground integrated Internet based on ground stations in the target ground station set leased in a reserved lease mode.

[0075] During the application process, the usage time of the ground station in the context of historical traffic can be obtained and compared with the time threshold that distinguishes the economic feasibility of the leasing model. If the threshold is exceeded, the reservation model is adopted. In other words, the usage time of the historical traffic data of subscribers of the integrated space-ground Internet is obtained. If the usage time exceeds the time threshold, the ground station in the target ground station set is determined to be leased under the reservation leasing model.

[0076] Furthermore, network performance optimization of the integrated space-ground Internet may be performed based on the ground stations in the target ground station set that are leased in a reserved lease mode.

[0077] In another embodiment, the present invention dynamically calculates the path of each incoming flow. First, the user pairs that generate traffic are calculated based on the predictable network topology. The candidate set of all serviceable ground station pairs , the ground station pairs in this candidate set meet the delay constraint If the candidate ground station set is not empty, the present invention will give priority to selecting a ground station from the set of ground stations rented in reservation mode. Otherwise, the ground station pair with the minimum transmission cost is selected for the user pair. However, if the candidate ground station set is empty, it means that a new ground station needs to be rented to meet the needs of the user pair. At this time, if If there are still ground station pairs that can serve the user pair (not meeting the delay constraint), the present invention will give priority to allocating ground stations to them and calculate the ground station that meets the delay constraint from the global candidate ground station candidate set. The subset of , sorted by estimated transmission cost from small to large and expanded to Then, when traffic for this user pair arrives again, the present invention selects a low-cost ground station pair for service, similar to the offline pre-allocated ground station pair. It is worth noting that the present invention ignores the time delay between leasing a ground station and its commissioning, as a ground station leased on demand can be considered "rented and used."

[0078] It is worth mentioning that when a new ground station is put into use In the example, they are quickly clustered into a ground station cluster according to their geographical location. Since the number of clusters is small, the present invention can quickly recalculate the LCs of all ground stations.

[0079] Figure 7 This is the second flow chart of the network performance optimization method of the integrated space-ground Internet provided by the present invention.

[0080] The following will be combined Figure 7 The process of the network performance optimization method of the integrated space-ground Internet is explained.

[0081] In an exemplary embodiment of the present invention, Figure 7 It can be seen that the network performance optimization method of the integrated space-ground Internet includes steps 710 to 750, and each step will be described below: In step 710, for any user pair, a set of available ground station pairs for the user pair is calculated, wherein the set of available ground station pairs is a set of candidate ground stations that meet the user delay constraint.

[0082] It should be noted that in order to cope with the high dynamics of LEO satellites, the present invention divides the continuous time period into a set of discrete time slices, and obtains the network topology structure on each time slice through predictable satellite trajectories; in order to reduce the combination space of candidate ground station pairs, the present invention utilizes a predictable satellite-to-ground connection method to aggregate time slices to reuse ground station pairs that can serve users on continuous time slices, effectively excluding ground stations that will not be used by users; in order to further reduce the number of leased ground stations and reduce the end-to-end delay of new user pairs arriving in the online stage, the present invention only leases and allocates ground stations with high delay contribution values ​​to user pairs. This contribution value measures the ability of a ground station to reduce the ground delay to other ground stations.

[0083] In one embodiment, the set of available ground station pairs for all communication user pairs at a certain time can be calculated. ,in, is based on and ,exist Time delay constraint Down That is, for any user pair, the set of available ground station pairs for the user pair is calculated.

[0084] In step 720, the sets of available ground station pairs of user pairs in adjacent discrete time slices are aggregated in chronological order, starting from the first discrete time slice until the last discrete time slice, and based on the aggregation results of user pairs in all discrete time slices, the same available ground stations in the aggregated ground station sets of user pairs in all discrete time slices are obtained.

[0085] In step 730, based on the same available ground stations in the aggregated ground station set of users in all discrete time slices, the ground station delay contribution value of the same available ground station is determined.

[0086] In step 740, the same available ground station with the largest ground station delay contribution value is used as the target ground station for the user pair.

[0087] In step 750, a set of target ground stations to be leased is determined based on the target ground stations of each user pair.

[0088] In one embodiment, for each user pair, Internal calculation The intersection, that is, in chronological order, starting from the first discrete time slice, the sets of available ground station pairs of user pairs in adjacent discrete time slices are aggregated in sequence until the last discrete time slice, and based on the aggregation results of user pairs in all discrete time slices, the same available ground stations in the aggregated ground station sets of user pairs in all discrete time slices are obtained.

[0089] If the intersection is empty at a certain moment, a ground station pair is selected from the intersection at the previous moment. Specifically, the following two steps can be taken: (1) If the intersection in the current time slice contains both ground station pairs, continue to aggregate the set of the next time slice; (2) Otherwise, select the ground station pair with higher latency contribution (LC).

[0090] Figure 5 It is a grayscale schematic diagram of time slice aggregation provided by the present invention. Figure 6 This is a color diagram of time slice aggregation provided by the present invention. Figure 5 and Figure 6 For readability, both the grayscale and color versions are included.

[0091] exist Figure 5 and Figure 6 In order to simplify the explanation, it is assumed that each ground station pair contains two identical ground stations. ,exist The intersection of serviceable ground station pairs has one pair included in the set of leased or private ground stations, so there is no need to lease a new ground station. , the intersection of the first time slice contains two ground stations that can be rented, so the controller will select one of the ground stations with a higher LC. Repeat the above steps until all user pairs are traversed and the controller obtains the final set of rented ground stations , that is, obtain the target ground station set to be rented.

[0092] Time slice aggregation can ensure that constraint (1) is satisfied under delay constraint (2) because The theoretical maximum can be almost reached. By excluding irrelevant ground stations, the one-time rental cost is also reduced.

[0093] In another exemplary embodiment of the present invention, the above-mentioned embodiment is continued as an example for description, wherein the ground station delay contribution value of the same available ground station can be determined in the following manner: Determine the inverse of the distances of the same available ground station to the centers of all other ground station clusters, and the respective weights of all other ground station clusters; The ground station delay contribution value of the same available ground station is determined by weighted summation based on the inverse of the distance from the same available ground station to the centers of all other ground station clusters and the respective weights of all other ground station clusters.

[0094] In one embodiment, ground stations are often built in places with dense user density, so some tracks can be covered by multiple ground stations simultaneously. Figure 7 After the controller has selected all the ground stations from the selected set, it is not necessary to rent all the ground stations because the usage time unit price or the one-time reservation fee is too high. If all the ground stations are rented, the cost will increase. The ground segment delay accounts for the main part of the end-to-end delay. Therefore, the controller calculates the time of a certain ground station. The delay contribution of each candidate ground station is estimated by multiplying the inverse of the distance to all other ground stations by the sum of the weights of other ground stations, that is, ,in, It is a user-configurable variable (corresponding to weight) used to measure the importance of a ground station, such as the traffic ratio of the service. is the physical distance between two nodes. The larger the contribution value, the lower the latency between the ground station and other ground stations.

[0095] In another embodiment, it is considered that private ground stations can provide the largest LC and set it to a large constant. However, some ground stations in remote areas, or ground stations that are close but only serve a few users will affect the calculation of LC. Therefore, the present invention clusters the ground stations to eliminate these outliers, such as using the K-means algorithm to divide the ground stations into multiple clusters. In each cluster, the negative impact of individual outliers will be weakened. Due to the distinct geographical distribution of ground stations, K-means can easily cluster them according to their distribution. Then the weight of a cluster is the sum of the weights of each ground station in it. Formally, assuming The center coordinate set of the cluster is , the cluster weight set is , the coordinates of the candidate ground stations are ,but The delay contribution is formula (5): (5) The LC of a ground station pair is the sum of the LCs of its two ground stations. Specifically, during the initialization phase, . Figure 8 It is a grayscale schematic diagram of the delay contribution value estimation provided by the present invention. Figure 9 is a color diagram of the delay contribution value estimation provided by the present invention, wherein: Figure 8 and Figure 9 are the same, for readability, both grayscale and color versions are included. Figure 8 and 9 As shown, in Of the two serviceable ground stations, is rented because it is Service ground station The ground delay between them is lower.

[0096] As described above, the network performance optimization method for a space-ground integrated internet provided by the present invention includes: determining a set of candidate ground stations based on historical traffic data of subscribers of the space-ground integrated internet and a predictable satellite-to-ground connection relationship of the space-ground integrated internet, wherein the candidate ground station set has a ground station-as-a-service capability; the predictable satellite-to-ground connection relationship is a link relationship between satellites and ground stations that is predictable for the space-ground integrated internet; determining a set of target ground stations to be leased from the set of candidate ground stations based on pre-established quality of service constraints and a pre-established cost model, so as to minimize the ground station leasing cost for network performance optimization of the space-ground integrated internet based on the target ground station set; and optimizing the network performance of the space-ground integrated internet based on the target ground station set. This method minimizes the ground station leasing cost of the space-ground integrated internet while meeting the network performance requirements of the space-ground integrated internet (i.e., optimizing the network performance).

[0097] The network performance optimization device of the integrated space-ground Internet provided by the present invention is described below. The network performance optimization device of the integrated space-ground Internet described below and the network performance optimization method of the integrated space-ground Internet described above can be referenced to each other.

[0098] Figure 10 It is a structural diagram of the network performance optimization device of the integrated space-ground Internet provided by the present invention.

[0099] In an exemplary embodiment of the present invention, Figure 10 It can be seen that the network performance optimization device of the integrated space-ground Internet can include a determination module 1010, a screening module 1020, and an optimization module 1030. Each module will be introduced below.

[0100] Determining module 1010 may be configured to determine a set of candidate ground stations based on historical traffic data of subscribers of the integrated space-ground internet and a predictable satellite-ground connection relationship of the integrated space-ground internet, wherein the set of candidate ground stations has a ground station as a service capability; the predictable satellite-ground connection relationship is a link relationship between satellites and ground stations that is predictable in the integrated space-ground internet; The screening module 1020 may be configured to determine a target ground station set to be leased from the candidate ground station set based on a pre-established quality of service constraint and a pre-established cost model, so as to minimize the ground station leasing cost for network performance optimization of the integrated space-ground internet based on the target ground station set; The optimization module 1030 may be configured to optimize the network performance of the integrated space-ground Internet based on the target ground station set.

[0101] In an exemplary embodiment of the present invention, the screening module 1020 may also be configured to: Dividing a continuous time period during which a user applies the integrated space-ground Internet into discrete time slices, wherein the discrete time slices include a plurality of moments; Determining a set of traffic demands generated by the user at different times; The screening module 1020 may determine the target ground station set to be leased from the candidate ground station set according to the pre-established quality of service constraints and the pre-established cost model in the following manner: Under the condition that the service quality constraint is met, based on the traffic demand sets generated by the users at different times, a target ground station set to be rented is determined from the candidate ground station set through a pre-built cost model.

[0102] In an exemplary embodiment of the present invention, the quality of service constraint includes a user service rate constraint; The screening module 1020 may pre-build the quality of service constraint in the following manner: Determining the number of serviceable user pairs, wherein the number of serviceable user pairs is the number of user pairs to which both the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are assigned serviceable ground stations, wherein the serviceable ground stations are ground stations in the set of target ground stations to be leased; Determine the number of user pairs for all user pairs; The user service rate constraint is constructed based on the number of serviceable user pairs and the number of user pairs of all user pairs.

[0103] In an exemplary embodiment of the present invention, the quality of service constraint includes a user delay constraint; The screening module 1020 may pre-build the quality of service constraint in the following manner: Determine the end-to-end delay for user pairs; Determining that the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are both allocated serviceable ground stations; The user delay constraint is constructed based on the end-to-end delay of the user pair and the allocation of serviceable ground stations to the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair.

[0104] In an exemplary embodiment of the present invention, the screening module 1020 may pre-build the cost model in the following manner: Constructing a data transmission cost function between ground stations and a cost function based on antenna usage time of ground stations; The cost model is constructed based on a data transmission cost function between ground stations and an antenna usage time cost function of a ground station.

[0105] In an exemplary embodiment of the present invention, the screening module 1020 may implement the pre-constructed data transmission cost function between ground stations in the following manner: determining a unit price of incoming traffic to a ground station in the set of candidate ground stations, a unit price of outgoing traffic to a ground station in the set of candidate ground stations, and a total amount of traffic generated by the user pair; A data transmission cost function between ground stations is constructed based on the incoming traffic unit price, the outgoing traffic unit price, and the total amount of traffic generated by the user pair.

[0106] In an exemplary embodiment of the present invention, the screening module 1020 may implement the pre-constructed antenna usage time cost function of the ground station in the following manner: Determine the unit price of the ground station based on the antenna usage time, and the unit price of the ground station based on the antenna usage time; Based on the antenna usage time-based unit price of the ground station and the antenna usage time-based cost function of the ground station, an antenna usage time-based cost function of the ground station is constructed.

[0107] In an exemplary embodiment of the present invention, the optimization module 1030 may also be configured to: Obtaining a historical traffic size, a geographic location, and an access satellite pair of a subscriber of the integrated space-ground internet, and calculating a ground station pair allocated to the subscriber based on the historical traffic size, the geographic location, and the access satellite pair; Based on the ground station pair allocated to the subscriber, obtaining statistics on antenna usage time of the ground station pair allocated to the subscriber; If the antenna usage time does not exceed a time threshold, determining that a ground station in the target ground station set is leased in an on-demand leasing mode; The optimization module 1030 may also optimize the network performance of the integrated space-ground Internet based on the target ground station set in the following manner: The ground stations in the target ground station set leased in an on-demand leasing mode optimize the network performance of the integrated space-ground Internet.

[0108] In an exemplary embodiment of the present invention, the optimization module 1030 may also be configured to: Obtaining a historical traffic size, a geographic location, and an access satellite pair of a subscriber of the integrated space-ground internet, and calculating a ground station pair allocated to the subscriber based on the historical traffic size, the geographic location, and the access satellite pair; Based on the ground station pair allocated to the subscriber, obtaining statistics of antenna usage time of the ground station pair allocated to the subscriber; When the antenna usage time exceeds a time threshold, determining that a ground station in the target ground station set is leased in a reserved lease mode; The optimization module 1030 can optimize the network performance of the integrated space-ground Internet based on the target ground station set in the following manner: Based on the ground stations in the target ground station set leased in a reserved lease mode, network performance of the integrated space-ground Internet is optimized.

[0109] In an exemplary embodiment of the present invention, the screening module 1020 may also be configured to: For any user pair, calculate the set of available ground station pairs for the user pair, where the set of available ground station pairs is a set of candidate ground stations that meets the user delay constraint; In chronological order, starting from the first discrete time slice, the sets of available ground station pairs of user pairs in adjacent discrete time slices are aggregated sequentially until the last discrete time slice, and based on the aggregation results of user pairs in all discrete time slices, the same available ground stations in the aggregated ground station sets of user pairs in all discrete time slices are obtained; Determine the ground station delay contribution value of the same available ground station in the aggregated ground station set based on the users in all discrete time slices; The same available ground station with the largest ground station delay contribution value is used as the target ground station for the user pair; Based on the target ground stations of each user pair, a set of target ground stations to be leased is determined.

[0110] In an exemplary embodiment of the present invention, the screening module 1020 may determine the ground station delay contribution value of the same available ground station in the following manner: Determining the reciprocal of the distance from the same available ground station to the centers of all other ground station clusters, and the respective weights of all other ground station clusters; Based on the inverse of the distance from the same available ground station to the center of all other ground station clusters and the respective weights of all other ground station clusters, the ground station delay contribution value of the same available ground station is determined by weighted summation.

[0111] Figure 11 An example of a physical structure diagram of an electronic device is shown below. Figure 11 As shown, the electronic device may include: a processor 1110, a communications interface 1120, a memory 1130, and a communications bus 1140, wherein the processor 1110, the communications interface 1120, and the memory 1130 communicate with each other via the communications bus 1140. The processor 1110 may invoke logic instructions in the memory 1130 to execute a method for optimizing network performance for a space-ground integrated internet. The method includes: determining a set of candidate ground stations based on historical traffic data of subscribers of the space-ground integrated internet and a predictable satellite-to-ground connection relationship of the space-ground integrated internet, wherein the set of candidate ground stations has a ground station-as-a-service capability; the predictable satellite-to-ground connection relationship is a predictable link relationship between satellites and ground stations in the space-ground integrated internet; determining a set of target ground stations to be leased from the set of candidate ground stations based on pre-established quality of service constraints and a pre-established cost model, so as to minimize the ground station leasing cost for optimizing network performance of the space-ground integrated internet based on the target ground station set; and optimizing network performance of the space-ground integrated internet based on the target ground station set.

[0112] Furthermore, the logic instructions in the aforementioned memory 1130 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0113] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the network performance optimization method of the integrated space-ground Internet provided by the above-mentioned methods, the method including: determining a set of candidate ground stations based on the historical traffic data of subscribed users of the integrated space-ground Internet and the predictable satellite-ground connection relationship of the integrated space-ground Internet, wherein the candidate ground station set has ground station as a service capability; the predictable satellite-ground connection relationship is a link relationship formed by satellites and ground stations that is predictable for the integrated space-ground Internet; determining a target ground station set to be rented in the candidate ground station set based on a pre-constructed service quality constraint and a pre-constructed cost model, so as to minimize the ground station rental cost for the network performance optimization of the integrated space-ground Internet based on the target ground station set; and optimizing the network performance of the integrated space-ground Internet based on the target ground station set.

[0114] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the network performance optimization method of the integrated space-ground Internet provided by the above-mentioned methods, the method comprising: determining a set of candidate ground stations based on the historical traffic data of subscribers of the integrated space-ground Internet and the predictable satellite-ground connection relationship of the integrated space-ground Internet, wherein the candidate ground station set has a ground station as a service capability; the predictable satellite-ground connection relationship is a link relationship formed by satellites and ground stations that is predictable for the integrated space-ground Internet; determining a target ground station set to be rented in the candidate ground station set based on a pre-constructed service quality constraint and a pre-constructed cost model, so as to minimize the ground station rental cost for the network performance optimization of the integrated space-ground Internet based on the target ground station set; and optimizing the network performance of the integrated space-ground Internet based on the target ground station set.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0116] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for optimizing network performance of a space-ground integrated Internet, characterized in that: The method comprises: Determining a set of candidate ground stations based on historical traffic data of subscribers of the integrated space-ground internet and a predictable satellite-to-ground connection relationship of the integrated space-ground internet, wherein the set of candidate ground stations has a ground station as a service capability; the predictable satellite-to-ground connection relationship is a link relationship between satellites and ground stations that is predictable in the integrated space-ground internet; determining a target ground station set to be leased from the candidate ground station set based on pre-established quality of service constraints and a pre-established cost model, so as to minimize a ground station lease cost for optimizing network performance of the integrated space-ground internet based on the target ground station set; Based on the target ground station set, network performance of the integrated space-ground Internet is optimized.

2. The network performance optimization method of the integrated space-ground Internet according to claim 1 is characterized in that: Before determining a target ground station set to be leased from the set of candidate ground stations according to the pre-built quality of service constraints and the pre-built cost model, the method further includes: Dividing a continuous time period during which a user applies the integrated space-ground Internet into discrete time slices, wherein the discrete time slices include a plurality of moments; Determining a set of traffic demands generated by the user at different times; The determining, based on the pre-established quality of service constraints and the pre-established cost model, a target ground station set to be leased from the candidate ground station set specifically includes: Under the condition that the service quality constraint is met, based on the traffic demand sets generated by the users at different times, a target ground station set to be rented is determined from the candidate ground station set through a pre-built cost model.

3. The method for optimizing network performance of the integrated space-ground Internet according to claim 2, characterized in that: The service quality constraint includes a user service rate constraint; The quality of service constraints are pre-constructed in the following way: Determining the number of serviceable user pairs, wherein the number of serviceable user pairs is the number of user pairs to which both the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are assigned serviceable ground stations, wherein the serviceable ground stations are ground stations in the set of target ground stations to be leased; Determine the number of user pairs for all user pairs; The user service rate constraint is constructed based on the number of serviceable user pairs and the number of user pairs of all user pairs.

4. The method for optimizing network performance of the integrated space-ground Internet according to claim 2, characterized in that: The service quality constraints include user delay constraints; The quality of service constraints are pre-constructed in the following way: Determine the end-to-end delay for user pairs; Determining that the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair are both allocated serviceable ground stations; The user delay constraint is constructed based on the end-to-end delay of the user pair and the allocation of serviceable ground stations to the satellite accessed by the source user in the user pair and the satellite accessed by the destination user in the user pair.

5. The method for optimizing network performance of the integrated space-ground Internet according to claim 2, characterized in that: The cost model is pre-built in the following way: Constructing a data transmission cost function between ground stations and a cost function based on antenna usage time of ground stations; The cost model is constructed based on a data transmission cost function between ground stations and an antenna usage time cost function of a ground station.

6. The method for optimizing network performance of the integrated space-ground Internet according to claim 5, characterized in that: The data transmission cost function between ground stations is constructed in the following way: determining a unit price of incoming traffic of a ground station in the set of candidate ground stations, a unit price of outgoing traffic of a ground station in the set of candidate ground stations, and a total amount of traffic generated by the user pair; A data transmission cost function between ground stations is constructed based on the incoming traffic unit price, the outgoing traffic unit price, and the total amount of traffic generated by the user pair.

7. The method for optimizing network performance of the integrated space-ground Internet according to claim 5, characterized in that: The antenna usage time cost function of the ground station is constructed in the following way: Determine the unit price of the ground station based on the antenna usage time, and the unit price of the ground station based on the antenna usage time; Based on the antenna usage time-based unit price of the ground station and the antenna usage time-based cost function of the ground station, an antenna usage time-based cost function of the ground station is constructed.

8. The method for optimizing network performance of the integrated space-ground Internet according to any one of claims 1 to 7, characterized in that: Before optimizing the network performance of the integrated space-ground Internet based on the target ground station set, the method further includes: Obtaining a historical traffic size, a geographic location, and an access satellite pair of a subscriber of the integrated space-ground internet, and calculating a ground station pair allocated to the subscriber based on the historical traffic size, the geographic location, and the access satellite pair; Based on the ground station pair allocated to the subscriber, obtaining statistics of antenna usage time of the ground station pair allocated to the subscriber; If the antenna usage time does not exceed a time threshold, determining that a ground station in the target ground station set is leased in an on-demand leasing mode; The optimizing the network performance of the integrated space-ground Internet based on the target ground station set specifically includes: The ground stations in the target ground station set leased in an on-demand leasing mode optimize the network performance of the integrated space-ground Internet.

9. The method for optimizing network performance of the space-ground integrated Internet according to any one of claims 1 to 7, characterized in that: Before optimizing the network performance of the integrated space-ground Internet based on the target ground station set, the method further includes: Obtaining a historical traffic size, a geographic location, and an access satellite pair of a subscriber of the integrated space-ground internet, and calculating a ground station pair allocated to the subscriber based on the historical traffic size, the geographic location, and the access satellite pair; Based on the ground station pair allocated to the subscriber, obtaining statistics of antenna usage time of the ground station pair allocated to the subscriber; When the antenna usage time exceeds a time threshold, determining that a ground station in the target ground station set is leased in a reserved lease mode; The optimizing the network performance of the integrated space-ground Internet based on the target ground station set specifically includes: Based on the ground stations in the target ground station set leased in a reserved lease mode, network performance of the integrated space-ground Internet is optimized.

10. The network performance optimization method of the integrated space-ground Internet according to claim 1, characterized in that: The method further comprises: For any user pair, calculate the set of available ground station pairs for the user pair, where the set of available ground station pairs is a set of candidate ground stations that meets the user delay constraint; In chronological order, starting from the first discrete time slice, the sets of available ground station pairs of user pairs in adjacent discrete time slices are aggregated sequentially until the last discrete time slice, and based on the aggregation results of user pairs in all discrete time slices, the same available ground stations in the aggregated ground station sets of user pairs in all discrete time slices are obtained; Determine the ground station delay contribution value of the same available ground station in the aggregated ground station set based on the users in all discrete time slices; The same available ground station with the largest ground station delay contribution value is used as the target ground station for the user pair; Based on the target ground stations of each user pair, a set of target ground stations to be leased is determined.

11. The method for optimizing network performance of the integrated space-ground Internet according to claim 10, characterized in that: The ground station delay contribution value of the same available ground station is determined in the following manner: Determining the reciprocal of the distance from the same available ground station to the centers of all other ground station clusters, and the respective weights of all other ground station clusters; Based on the inverse of the distance from the same available ground station to the center of all other ground station clusters and the respective weights of all other ground station clusters, the ground station delay contribution value of the same available ground station is determined by weighted summation.

12. A network performance optimization device for a space-ground integrated Internet, characterized in that: The device comprises: a determination module configured to determine a set of candidate ground stations based on historical traffic data of subscribers of the integrated space-ground internet and a predictable satellite-ground connection relationship of the integrated space-ground internet, wherein the set of candidate ground stations has a ground station as a service capability; the predictable satellite-ground connection relationship is a link relationship between satellites and ground stations that is predictable in the integrated space-ground internet; a screening module, configured to determine a target ground station set to be leased from the candidate ground station set based on a pre-established quality of service constraint and a pre-established cost model, so as to minimize a ground station lease cost for optimizing network performance of the integrated space-ground internet based on the target ground station set; An optimization module is used to optimize the network performance of the integrated space-ground Internet based on the target ground station set.

Images