CN107659666A - Real-time video dissemination system and method based on mobile subscriber - Google Patents

Abstract

The present invention relates to a real-time video distribution system and method based on mobile users. The system includes: a control layer and a data layer; the control layer includes an SDN controller; the data layer is used to receive the scheduling result of the control layer Forwarding data and maintaining video content; this method is applied to the control layer, including: obtaining real-time video requests from mobile users to form a group of video distribution sessions; configuring session data streams, performing space and spectrum scheduling, and combining session-based routing constraints Obtain a scheduling result; send the scheduling result to the data layer. The invention satisfies mobile users' requirements for diversity and flexibility of real-time video requirements, realizes flexible control of flow, and effectively manages resources and optimizes resource allocation according to network environment changes.

Description

System and method for real-time video distribution based on mobile users

technical field

The invention belongs to the technical field of real-time video distribution network, and in particular relates to a real-time video distribution system and method based on mobile users.

Background technique

In recent years, emerging video services have led to a substantial increase in Internet traffic. In 2015, global video traffic accounted for 70% of all consumer Internet traffic and will reach 82% in 2020. With the development of the mobile Internet, mobile users will become the main consumers of Internet video; for example, as the fourth largest Internet traffic producer, Twitch provides more than 150 billion minutes of live video every month, which are generated by mobile users. Therefore, it is a challenging task to satisfy the explosive demand of mobile users for real-time video.

Video delivery network (Video Delivery Network, VDN for short) service has attracted much attention as a main video content distribution mode. However, VDN has some disadvantages; on the one hand, most VDNs rely on pre-deployed infrastructure and statically configured network topology; on the other hand, the VDN structure is not suitable for small video providers because they do not have the It inevitably hinders the development of VDN.

Cellular networks are also challenged to handle the explosive growth in network traffic due to the prevalence of high data rate video. First, random video requests require fast and efficient resource allocation, but devices and protocols in current cellular networks cannot support dynamic configuration; second, the random mobility of users makes it difficult for base stations to cover all mobile users.

To sum up, there is still no effective solution to the problem that the video distribution network in the prior art cannot meet the diversity and flexibility of mobile users' demands for real-time video.

Contents of the invention

Aiming at the deficiencies in the prior art and solving the problem that the video distribution network in the prior art cannot meet the diversity and flexibility of mobile users' demand for real-time video, the present invention provides a real-time video distribution system and method based on mobile users, Specifically, it is a software-defined real-time video distribution network (S-VDN) system with D2D communication and its data distribution method, which realizes flexible control of network traffic, effective resource management and optimized resource allocation according to changes in network conditions.

The first object of the present invention is to provide a real-time video distribution system based on mobile users.

In order to achieve the above object, the present invention adopts the following technical scheme:

A real-time video distribution system based on mobile users, the system includes: a control layer and a data layer;

The control layer, including an SDN controller, is used to obtain real-time video requests from mobile users to form a group of video distribution sessions, configure session data streams, perform space and spectrum scheduling, and obtain scheduling results based on session-based routing constraints, and send dispatching results to said data layer;

The data layer is used to receive the scheduling result forwarding data of the control layer and maintain video content.

As a further preferred solution, the SDN controller obtains real-time video requests from different mobile users to the original server to form a group of video distribution sessions;

Each video distribution session in the set of video distribution sessions includes a corresponding data stream characterized by a node pair between the mobile user and the origin server.

In the present invention, a new video distribution network VDN model system is proposed. In the control layer, the SDN controller obtains real-time video requests from different mobile users to the original server to form a group of video distribution sessions, and uses the session mechanism to manage data flow. , and adopt protocol rules based on data flow, after the scheduling result is formed in the control layer, it is sent to the data layer for data forwarding, which avoids frequent interaction between the data layer and the control layer.

As a further preferred solution, the control layer of the system specifically adopts a path division scheduling method to configure video distribution session data streams.

In the present invention, adopting the path division scheduling method to configure the session data flow effectively improves the data flow receiving rate and resource utilization rate of the VDN.

As a further preferred solution, the control layer of the system is also specifically used for:

Mobile users are divided according to whether they are within the coverage of the base station:

For mobile users who send real-time video requests within the coverage of the base station, selectively obtain real-time video data from the base station or obtain real-time video data through D2D communication between mobile users;

For mobile users who do not send real-time video requests within the coverage of the base station, real-time video data can be obtained through D2D communication between mobile users.

In the present invention, for mobile users who send real-time video requests within the coverage of the base station, real-time video data is selectively obtained from the base station or through D2D communication between mobile users, effectively reducing the traffic load of the base station.

As a further preferred solution, the control layer is also specifically configured to optimize data flow scheduling by adopting a multi-commodity flow method.

The second object of the present invention is to provide a real-time video distribution method based on mobile users.

In order to achieve the above object, the present invention adopts the following technical scheme:

A real-time video distribution method based on mobile users, the method is applied to the control layer, including:

Obtain real-time video requests from mobile users to form a group of video distribution sessions;

Configure session data flow, perform space and spectrum scheduling, and combine session-based routing constraints to obtain scheduling results;

Send the scheduling result to the data layer.

As a further preferred solution, in this method, the acquisition of the mobile user's real-time video request forms a group of video distribution sessions, specifically including:

Obtain real-time video requests from different mobile users to the original server to form a group of video distribution sessions;

Each video distribution session in the set of video distribution sessions includes a corresponding data stream characterized by a node pair between the mobile user and the origin server.

As a further preferred solution, in the method, the configuring session data flow specifically includes: configuring the video distribution session data flow using a path division scheduling method.

As a further preferred solution, in this method, before performing space and spectrum scheduling, it is judged whether the mobile user is within the coverage of the base station,

If so, use spectrum scheduling to allocate channels and combine space scheduling to determine the user cluster of mobile users, and selectively obtain real-time video from the base station or obtain real-time video through D2D communication between mobile users;

Otherwise, only the user clusters of mobile users are determined according to spatial scheduling, and real-time video data is obtained through D2D communication between mobile users.

As a further preferred solution, in the method, the space scheduling specifically includes:

The user cluster of the mobile user is determined within the physical range that the mobile user can cover by using the physical distance between the mobile user and other nodes.

As a further preferred solution, in this method, the spectrum scheduling specifically includes:

Orthogonal sub-channel method is used to allocate channels for mobile users to send and/or receive real-time video data; while spectrum scheduling needs to meet the rules of space scheduling.

As a further preferred solution, in this method, the session-based routing constraints include:

The nodes in the video distribution session meet the traffic balance principle;

and

The total traffic of all channels on each routing link shall not exceed the total capacity of the routing link.

As a further preferred solution, in this method, the multi-commodity flow method is used to optimize the data flow scheduling, and the transmission cost is minimized on the basis of satisfying the routing constraints based on the session, and the optimal solution is calculated using a heuristic method.

As a further preferred solution, in this method, the multi-commodity flow method specifically includes:

Find mobile users who meet storage constraints;

Determine the best route from the origin server to the selected mobile user.

As a further preferred solution, in this method, a heuristic method is used to obtain two multi-commodity flow algorithms according to the specific steps of the multi-commodity flow method, and they are compared from the aspects of acceptance rate, income, cost and bandwidth utilization, and the comprehensive calculation Optimal solution.

In the present invention, a real-time video distribution method based on mobile users is optimized by using the multi-commodity method combined with the above-mentioned session-based routing constraints, which can not only meet the real-time video distribution requests of mobile users, but also minimize the transmission cost.

Beneficial effects of the present invention:

1. A mobile user-based real-time video distribution system and method according to the present invention realizes flexible control of network traffic, and performs effective resource management and optimized resource allocation according to changes in network conditions.

2. In the mobile user-based real-time video distribution system and method of the present invention, in the control layer, the SDN controller obtains real-time video requests from different mobile users to the original server to form a group of video distribution sessions, and uses the session mechanism to manage Data flow, and adopt the protocol rules based on data flow, after the control layer forms the scheduling result, send it to the data layer for data forwarding, avoiding the frequent interaction between the data layer and the control layer.

3. A new video distribution network VDN model system according to the present invention adopts the path division scheduling method to configure the session data flow to effectively improve the data flow receiving rate and resource utilization rate of the VDN.

4. A mobile user-based real-time video distribution system and method according to the present invention uses a multi-commodity method to optimize a mobile user-based real-time video distribution method based on session-based routing constraints, which can satisfy mobile user requirements. Real-time video distribution requests while minimizing transmission costs.

Description of drawings

The accompanying drawings constituting a part of the present application are used to provide further understanding of the present application, and the schematic embodiments and descriptions of the present application are used to explain the present application, and do not constitute improper limitations to the present application.

Fig. 1 is a system structure diagram among the present invention;

Fig. 2 is a model diagram of the software-defined S-VDN in the present invention;

Fig. 3 is the network topology diagram of existing VDN;

Fig. 4 is the network topology diagram of S-VDN among the present invention;

Fig. 5 is a flow chart of the method in the present invention;

Fig. 6 is the comparison schematic diagram of two kinds of multi-commodity flow methods in the present invention in receiving rate and time;

Fig. 7 is the comparative schematic diagram of two kinds of multi-commodity flow methods in the present invention in average income and time;

Fig. 8 is a comparative schematic diagram of the average cost and time of two multi-commodity flow methods in the present invention;

FIG. 9 is a schematic diagram of comparison of bandwidth utilization and time between two multi-commodity flow methods in the present invention.

Detailed ways:

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

It should be pointed out that the following detailed description is exemplary and intended to provide further explanation to the present application. Unless otherwise specified, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and/or combinations thereof.

Aiming at the deficiencies in the prior art and solving the problem that the video distribution network in the prior art cannot meet the diversity and flexibility of mobile users' demand for real-time video, the present invention provides a real-time video distribution system and method based on mobile users, Specifically, it is a software-defined real-time video distribution network (S-VDN) system with D2D communication and its data distribution method, which realizes flexible control of network traffic, effective resource management and optimized resource allocation according to changes in network conditions.

In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

Example 1:

The purpose of Embodiment 1 is to provide a real-time video distribution system based on mobile users.

In order to achieve the above object, the present invention adopts the following technical scheme:

As shown in Figure 1,

A real-time video distribution system based on mobile users, the system includes: a control layer and a data layer;

The control layer includes an SDN controller with a VDN global view to collect mobile user requests and schedule wireless spectrum resources; configure session data streams, perform space and spectrum scheduling, and combine session-based routing constraints to obtain scheduling results and send scheduling results to said data layer;

The data layer is used to receive the scheduling result forwarding data of the control layer and maintain video content.

In the present invention, a new VDN model system for video distribution network is proposed, S-VDN, and SDN controller is an application program in software-defined network SDN, which is responsible for flow control to ensure an intelligent network. In the control layer, the SDN controller obtains real-time video requests from different mobile users to the original server to form a group of video distribution sessions, uses the session mechanism to manage data flow, and adopts protocol rules based on data flow, and sends them after the scheduling result is formed at the control layer Data forwarding to the data layer avoids frequent interaction between the data layer and the control layer.

as shown in picture 2,

It should be noted that it is assumed that one VDN can support one provider (or origin server), and the origin server replicates video content at multiple cloud sites (or proxy sites) in order to provide requested services to all mobile users. The software-defined VDN model is shown in Figure 2. O represents the original server, and the line represents the potential delivery path. The solid line represents the communication between the original server and the base station, and the dotted line represents the communication between mobile users. Mobile users (e.g. n1–n5) in the shaded area covered by the base station can get real-time video directly from the base station. In order to reduce the traffic load of the base station, some mobile users (such as n4, n5) choose D2D communication to obtain real-time video content. On the other hand, mobile users (such as n6–n8) who are not within the coverage of the base station can only adopt D2D communication.

Therefore, during real-time video distribution, mobile users can be treated as edge servers to replicate videos from the original server. Therefore, the mobile user can obtain real-time video directly from the base station, and can also obtain real-time video from the mobile user through D2D communication.

In this embodiment, when a mobile user sends a video request, the SDN controller at the control layer performs fast and effective data flow allocation, which mainly consists of three parts: session-based flow scheduling, path segmentation scheduling, and space and spectrum scheduling:

Session-based stream scheduling:

Specifically, the SDN controller constructs a group of video distribution sessions for obtaining real-time video requests from different mobile users to the original server, and each video distribution session in the group of video distribution sessions includes a corresponding connection between the mobile user and the original server. data flow characterized by node pairs;

Path split scheduling:

The SDN controller is also used to configure the video distribution session data flow using the path segmentation scheduling method; the path segmentation scheduling method configures the session data flow to effectively improve the data flow receiving rate and resource utilization of the VDN.

It should be noted that it is assumed that each mobile user can visit multiple distribution delay nodes. If the VDN does not support route segmentation, the receiving rate and resource utilization of the VDN will be reduced. As shown in Figure 3(a), the schematic diagram of the existing VDN, the number next to the link is the bandwidth of this link. There are two mobile users U ₅ and U ₆ sending requests to the original server O at the same time and the requested bandwidth is 500bps. They are all close to the user U ₄ . When considering the link bandwidth capacity limitation, the bandwidth on the U ₂ -U ₄ link is 400bps, which cannot meet the requested bandwidth. Therefore, the distribution route must choose U ₁ -U ₄ . But the bandwidth on the link U ₁ -U ₄ is 800bps, and at most one request can be satisfied, as shown in Figure 3(b) and (c).

In this embodiment, the SDN controller adopts the path division scheduling method to configure the video distribution session data flow, which can meet the above user's request. The main idea of path splittable scheduling is: S-VDN network topology, as shown in Figure 4(a), it is the same as Figure 3(a) network topology and user requests, the difference between the two methods is that the path splitting method supports Multiple links provide bandwidth to each mobile user. As shown in Figure 4(b), the request of the end user U ₅ is satisfied through the link OU ₁ -U ₄ -U ₅ . Since the link U ₁ -U ₄ has allocated 500bps bandwidth to the mobile user U ₅ , and there is 300bps left, the request of the user U ₆ has to pass through two paths OU ₁ -U ₄ -U ₆ and O–U ₂ -U ₄ -U ₆ Satisfy the request. On the other hand, it is also possible to assign one path OU ₁ -U ₄ -U ₆ to U ₆ and two paths to U ₅ :

OU ₁ -U ₄ -U ₅ and O–U ₂ -U ₄ -U ₅ , as shown in Fig. 4(c).

Space and Spectrum Scheduling:

The SDN controller is also used for space and spectrum scheduling, and combines session-based routing constraints to obtain scheduling results, and sends the scheduling results to the data layer;

The SDN controller is also used to divide mobile users according to whether they are within the coverage of the base station:

For mobile users who send real-time video requests within the coverage of the base station, selectively obtain real-time video data from the base station or obtain real-time video data through D2D communication between mobile users;

For mobile users who do not send real-time video requests within the coverage of the base station, real-time video data can be obtained through D2D communication between mobile users.

In the present invention, for mobile users who send real-time video requests within the coverage of the base station, real-time video data is selectively obtained from the base station or through D2D communication between mobile users, effectively reducing the traffic burden of the base station.

The SDN controller is also specifically used for: adopting a multi-commodity flow method to optimize data flow scheduling.

Example 2:

The purpose of Embodiment 2 is to provide a real-time video distribution method based on mobile users.

In order to achieve the above object, the present invention adopts the following technical scheme:

As shown in Figure 5,

A real-time video distribution method based on mobile users, the method is applied to the control layer, including:

Step (1): Obtain the real-time video request of the mobile user to form a group of video distribution sessions;

In described step (1), mobile user sends out video request, visits a plurality of access points, and the SDN controller of the control layer of the real-time video distribution system based on mobile user of the present embodiment obtains the real-time video request of mobile user to form a group A video distribution session, specifically including:

Obtain real-time video requests from different mobile users to the original server to form a group of video distribution sessions;

Each video distribution session in the set of video distribution sessions includes a corresponding data stream characterized by a node pair between the mobile user and the origin server.

Step (2): Configure session data flow, perform space and spectrum scheduling, and combine session-based routing constraints to obtain scheduling results;

In the step (2), the configuration of the session data flow specifically includes: configuring the video distribution session data flow using a path division scheduling method. Multiple links are allowed to provide bandwidth to each mobile user.

In the step (2), before performing space and spectrum scheduling, it is judged whether the mobile user is within the coverage of the base station,

If so, spectrum scheduling is used to allocate channels combined with spatial scheduling to determine the user cluster of mobile users, time and spectrum scheduling are used to allocate channels, and mobile users selectively obtain real-time video from the base station or through D2D communication between mobile users;

Otherwise, only the user clusters of mobile users are determined according to spatial scheduling, and real-time video data is obtained through D2D communication between mobile users.

In the step (2), the space scheduling specifically includes:

The user cluster of the mobile user is determined within the physical range that the mobile user can cover by using the physical distance between the mobile user and other nodes.

In spatial scheduling, mobile users within the coverage area of a base station make incoming requests. Assume that each mobile user has an associated non-negative value D _u that represents the physical range that the user can cover.

Then the user cluster of each mobile user u for:

Among them, dis() is a function to calculate the physical distance between two nodes, n is a node, and N is all mobile user nodes.

In the step (2), the spectrum scheduling specifically includes:

Orthogonal sub-channel method is used to allocate channels for mobile users to send and/or receive real-time video data; while spectrum scheduling needs to meet the rules of space scheduling.

In spectrum scheduling, this embodiment only focuses on spectrum-based channel allocation, that is, how to allocate channels to mobile users for sending and receiving videos. In this embodiment, different mobile users use an orthogonal sub-channel method.

Assuming that channel k is available to both mobile user i and mobile user j, it is expressed as:

Among them, channel k∈K _i ∩K _j , K={1,2,…,k,…,K} represents the set of all sub-channels in the system, Denotes the set of channels available to the user (i,j∈N), K _i ≠K _j .

For a mobile user i∈N and a channel k∈K _i :

in Denotes the set of users who can access channel k and are within the transmission range of user i.

In the step (2), the session-based routing constraints include:

The nodes in the video distribution session meet the traffic balance principle;

and

The total traffic of all channels on each routing link shall not exceed the total capacity of the routing link.

Among them, the traffic balance of node i in each video distribution session l is described by the following equation:

First, if the original server is the source node of the video distribution session l, i=s(l), then

where f _ij (l) denotes the data rate on the link attributed to session l, where i, j ∈ H; r(l) denotes the traffic request per session l.

Second, if node i is an intermediate relay node of video distribution session l, i.e. i≠s(l) and i≠d(l), then

Again, if mobile user i is the end point of video distribution session l, i.e. i=d(l), then

The total flow of all channels on each routing link does not exceed the total capacity of the routing link:

The constraint on link (i,j) capacity can be expressed as:

in, P _t represents the power spectral density of the transmitter, n is the path loss coefficient, μ is the relevant antenna constant, and d _ij represents the distance between nodes i and j.

In the step (2), the multi-commodity flow method is used to optimize the data flow scheduling, and the transmission cost is minimized on the basis of satisfying the session-based routing constraints, and the optimal solution is calculated using a heuristic method.

The multi-commodity flow problem is proposed for the optimization problem that can satisfy the real-time video requests of mobile users and minimize the transmission cost, namely:

Equation (8) depends on the following conditions:

Among them, σ _ij represents the unit price of wireless bandwidth allocated by flow f _ij (l), and z _ij is the storage place of mobile users. Principle of Flow Conservation Equations (9), (10) and (11) specify the routing constraints, and Equation (12) states that the total traffic flow routed through the link e(i,j) cannot exceed the total transmission of e(i,j) capacity, constraints (13) and (14) provide variables f _ij (l) and Constraint domain, the constraint condition (15) is that the storage of the access user z _ij should meet the requirement c(l).

The multi-commodity flow method specifically includes:

Find mobile users who meet storage constraints;

Determine the best route from the origin server to the selected mobile user.

In this method, a heuristic method is used to obtain two multi-commodity flow algorithms according to the specific steps of the multi-commodity flow method, and they are compared in terms of acceptance rate, income, cost and bandwidth utilization, and the optimal solution is comprehensively calculated.

In this embodiment, two heuristic methods are used for analysis: optimal MCF algorithm (O-MCF) and greedy MCF algorithm (G-MCF).

In the S-VDN scenario, the network parameters and user parameters are set for simulation, and the performance of the optimized MCF algorithm (O-MCF) and the greedy MCF algorithm (G-MCF) are compared according to the experimental results.

The network parameters are set as follows:

(1) Simulate a 100×100 S-VDN scenario with 25 nodes in the GT-ITM tool.

(2) Storage capacity and link bandwidth are evenly distributed between 50 and 100.

(3) The real-time video duration obeys Poisson distribution (λ=0.05, μ=500).

The user parameters are set as follows:

(4) The number of video users obeys the uniform distribution U(6,10).

(5) User storage and bandwidth requests obey the uniform distribution U(0,10).

(6) The maximum coverage is D _u =25.

Analysis of results:

First, Fig. 6 describes the acceptance rate of real-time video by O-MCF and G-MCF algorithms, because O-MCF uses routing constraints to coordinate the access node selection problem, which makes it easy for MCF to find a suitable route, so O-MCF accepts rate is higher.

Second, as can be seen from Figure 7, O-MCF significantly outperforms G-MCF in terms of average revenue performance over time. Experimental results show that the O-MCF algorithm distributes more profitable video content, rather than just distributing small video content to increase revenue.

Third, the experimental results in Figures 8 and 9 show that both algorithms have similar lease costs and bandwidth utilization. O-MCF sometimes has higher cost and lower bandwidth utilization than G-MCF because higher reception rate results in higher allocation bandwidth and storage.

In the present invention, a real-time video distribution method based on mobile users is optimized by using the multi-commodity method combined with the above-mentioned session-based routing constraints, which can not only meet the real-time video distribution requests of mobile users, but also minimize the transmission cost.

Step (3): sending the scheduling result to the data layer.

Those skilled in the art should understand that each module or each step of the present invention described above can be realized by a general-purpose computer device, and optionally, they can be realized by a program code executable by the computing device, thereby, they can be stored in The storage device is executed by the computing device, or they are manufactured as individual integrated circuit modules, or multiple modules or steps among them are manufactured as a single integrated circuit module. The invention is not limited to any specific combination of hardware and software.

Beneficial effects of the present invention:

1. A mobile user-based real-time video distribution system and method according to the present invention realizes flexible control of network traffic, and performs effective resource management and optimized resource allocation according to changes in network conditions.

2. In the mobile user-based real-time video distribution system and method of the present invention, in the control layer, the SDN controller obtains real-time video requests from different mobile users to the original server to form a group of video distribution sessions, and uses the session mechanism to manage Data flow, and adopt the protocol rules based on data flow, after the control layer forms the scheduling result, send it to the data layer for data forwarding, avoiding the frequent interaction between the data layer and the control layer.

3. A new video distribution network VDN model system according to the present invention adopts the path division scheduling method to configure the session data flow to effectively improve the data flow receiving rate and resource utilization rate of the VDN.

4. A mobile user-based real-time video distribution system and method according to the present invention uses a multi-commodity method to optimize a mobile user-based real-time video distribution method based on session-based routing constraints, which can satisfy mobile user requirements. Real-time video distribution requests while minimizing transmission costs.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the present application. For those skilled in the art, there may be various modifications and changes in the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A real-time video distribution system based on mobile users, the system comprising: a control layer and a data layer;

the control layer comprises an SDN controller and is used for acquiring a real-time video request of a mobile user to form a group of video distribution sessions, configuring session data streams, performing space and spectrum scheduling, obtaining a scheduling result by combining a session-based routing constraint condition, and sending the scheduling result to the data layer;

and the data layer is used for receiving the scheduling result forwarding data of the control layer and maintaining video content.

2. The mobile subscriber-based real-time video distribution system of claim 1, wherein the SDN controller constructs a set of video distribution sessions from different mobile subscriber-to-origin server real-time video requests;

each video distribution session in the set of video distribution sessions includes a corresponding data stream characterized by a pair of nodes between the mobile user and the origin server.

3. The system of claim 1, wherein the control layer configures the video distribution session data stream by a path splitting scheduling method.

4. The system for real-time video distribution based on mobile subscribers of claim 1, wherein the control layer of the system is further specifically configured to:

dividing the mobile users according to whether the mobile users are in the coverage area of the base station:

for mobile users sending real-time video requests within the coverage range of a base station, selectively acquiring real-time video data from the base station or acquiring the real-time video data through D2D communication among the mobile users;

for mobile users who do not make real-time video requests within the coverage of the base station, real-time video data is obtained through D2D communication between the mobile users.

5. The system of claim 1, wherein the control layer is further configured to optimize data flow scheduling using a multi-commodity flow method.

6. A real-time video distribution method based on mobile users, which is applied to the control layer of a real-time video distribution system based on mobile users as claimed in any one of claims 1-5, and which comprises:

acquiring a real-time video request of a mobile user to form a group of video distribution sessions;

configuring conversation data flow, carrying out space and spectrum scheduling, and obtaining a scheduling result by combining with a routing constraint condition based on conversation;

and sending a scheduling result to the data layer.

7. The method according to claim 6, wherein the obtaining of the real-time video request of the mobile user forms a group of video distribution sessions, and specifically comprises:

acquiring real-time video requests from different mobile users to an original server to construct a group of video distribution sessions;

each video distribution session in the set of video distribution sessions includes a corresponding data stream characterized by a pair of nodes between a mobile user and an origin server;

the configuring the session data stream specifically includes: and configuring the video distribution session data stream by adopting a path division scheduling method.

8. The method according to claim 6, wherein before performing space and spectrum scheduling, the method determines whether the mobile user is in a coverage area of a base station, if so, determines a user cluster of the mobile user by using a spectrum scheduling allocation channel and combining the space scheduling, and selectively obtains a real-time video from the base station or obtains the real-time video through D2D communication between the mobile users;

otherwise, the user cluster of the mobile users is determined only according to the spatial scheduling, and the real-time video data is obtained through D2D communication among the mobile users.

9. The method according to claim 6, wherein the spatial scheduling specifically includes:

determining a user cluster of the mobile user in a physical range which can be covered by the mobile user by adopting the physical distance between the mobile user and other nodes;

in the method, the spectrum scheduling specifically includes:

allocating channels for transmitting and/or receiving real-time video data by the mobile user by adopting an orthogonal subchannel method; the spatial scheduling rule is required to be met during the frequency spectrum scheduling;

as a further preferred solution, in the method, the session-based routing constraint condition includes:

nodes in the video distribution session meet the flow balance principle;

and

the total traffic of all channels on each routing link does not exceed the total capacity of that routing link.

10. The method of claim 6, wherein a multi-commodity flow method is used to optimize data flow scheduling, transmission cost is minimized on the basis of meeting session-based routing constraint conditions, and a heuristic method is used to calculate an optimal solution;

in the method, the multi-commodity flow method specifically comprises the following steps:

searching for mobile users meeting storage constraints;

determining the optimal route from the original server to the selected mobile user;

in the method, a heuristic method is adopted to obtain two multi-commodity flow algorithms according to the specific steps of the multi-commodity flow method, and the algorithms are compared respectively from the aspects of acceptance rate, income, cost and bandwidth utilization rate, so that the optimal solution is comprehensively calculated.