A multi-server communication switching method, system and storage medium

Abstract

The present invention discloses a multi-server communication switching method, system and storage medium, which relates to the field of communication service technology, including: determining the best communication area of ​​each server within the coverage of the multi-server communication network; determining the maximum communication load of each server; obtaining all device terminals connected to the multi-server communication network; obtaining the position change trajectory of each device terminal; predicting the total number of device terminals in the best communication area of ​​each server within the coverage of the multi-server communication network at each time point within a preset time period; judging whether the predicted device terminal data of the best communication area of ​​each server exceeds the maximum communication load of the corresponding server. The advantages of the present invention are: realizing pre-prediction adjustment of server communication services, ensuring the stability of users during multi-server communication switching, thereby ensuring the stability of communication connections between users and multiple servers, and improving user experience.

Description

Technical Field

[0001] The present invention relates to the field of communication service technology, and in particular to a multi-server communication switching method, system and storage medium. Background Art

[0002] With the rapid development of the Internet (mobile Internet), users are increasingly dependent on data services provided by servers, and their demand for data availability is increasing. They need to access the services (data) provided by servers anytime and anywhere. In order to ensure the communication stability of users, the existing technology adopts a multi-server hot standby solution to switch the server that provides services to users based on the user's own dynamic needs.

[0003] However, in the prior art, due to the lack of effective dynamic analysis of user needs to predict user behavior, it is difficult to dynamically adjust and switch servers based on user behavior, and it is difficult to achieve smooth switching of communications between users and servers, which affects user experience. Summary of the invention

[0004] In order to solve the above technical problems, a multi-server communication switching method, system and storage medium are provided. This technical solution solves the above-mentioned problems of lack of effective dynamic analysis of user needs to predict user behavior, difficulty in dynamically adjusting and switching servers based on user behavior, difficulty in achieving smooth switching of communications between users and servers, and affecting user experience.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A multi-server communication switching method, comprising:

[0007] Determine the best communication area for each server within the coverage of the multi-server communication network;

[0008] Determine the maximum communication load for each server;

[0009] Obtain all device terminals connected to the multi-server communication network;

[0010] Continuously obtain the location information of each device terminal in real time to obtain the location change trajectory of each device terminal;

[0011] Based on the position change trajectory of each device terminal, predict the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network within a preset time period, and record it as predicted device terminal data;

[0012] Determine whether the predicted device terminal data of the optimal communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, establish a communication connection between all device terminals corresponding to the predicted device terminal data and the corresponding server. If so, adjust the communication server of each device terminal based on the communication optimization algorithm.

[0013] Preferably, the determining of the best communication area for each server within the coverage of the multi-server communication network specifically includes:

[0014] Construct a positioning coordinate system within the coverage of the multi-server communication network;

[0015] Determine the physical location coordinates of each server in the positioning coordinate system;

[0016] Calculate the service communication index of each server at each location within the coverage of the multi-server communication network through a service communication index calculation formula;

[0017] Determine the server with the smallest service communication index at each location within the coverage of the multi-server communication network, and record the location as the best communication location for the server;

[0018] Determine the area consisting of all the best communication locations of each server, which is the best communication area of ​​the server;

[0019] The service communication indicator calculation formula is:

[0020]

[0021] Where, T i (x, y) is the service communication index of the i-th server for the position with coordinates (x, y) in the positioning coordinate system, Q i is the stability index of the i-th server, n is the total number of servers in the multi-server communication network, x i is the horizontal coordinate of the ith server in the positioning coordinate system, y i is the ordinate of the ith server in the positioning coordinate system, x is the abscissa of the position with coordinates (x, y) in the positioning coordinate system, and y is the ordinate of the position with coordinates (x, y) in the positioning coordinate system.

[0022] Preferably, the method for determining the stability index of the server is:

[0023] Determine the running status of the server and collect statistics on the running data of multiple servers of the same type in the same running status;

[0024] Based on the operating data of multiple servers of the same type under the same operating status, a logistics regression prediction model is constructed;

[0025] Based on the logistics regression prediction model, the probability of failure of the current server is determined and used as the stability indicator of the server;

[0026] The logistics regression prediction model is specifically:

[0027]

[0028] Where Q is the probability of server failure, T is the working time of the server, and α and β are the coefficients of the logistics regression prediction model.

[0029] Preferably, the communication optimization algorithm is specifically:

[0030] According to the position change trajectory of each device terminal, the device terminal whose optimal communication area changes within the preset time period is recorded as a changed device terminal;

[0031] For all other device terminals except the changed device terminal, the communication connection between the device terminal and the original server is maintained;

[0032] Based on the position change trajectory of the changing device terminal, the communication weight between the changing device terminal and each server is determined respectively;

[0033] Calculate the communication switching index between each changing device terminal and each server respectively;

[0034] Building communication restriction conditions based on the maximum communication load of each server and the device communication connection status of each server;

[0035] Determine the communication server corresponding to each variable device terminal under the condition of communication restriction so that the total communication switching index of all variable device terminals is minimized.

[0036] Preferably, the communication weight between the changing device terminal and each server is determined based on the position change track of the changing device terminal as follows:

[0037] Adding a first communication weight to the server corresponding to the best communication area to which the changed device terminal moves, adding a second communication weight to the server corresponding to the initial best communication area where the changed device terminal is located, and adding a third communication weight to the remaining servers;

[0038] Among them, the first communication weight>the second communication weight>the third communication weight.

[0039] Preferably, the calculation formula for the communication switching index between the changing device terminal and each server is:

[0040]

[0041] In the formula, B i is the communication switching index between the i-th server and the changing device terminal, A i is the communication weight between the ith server and the changing device terminal, X is the horizontal coordinate of the changing device terminal in the positioning coordinate system within the preset time period, and Y is the vertical coordinate of the changing device terminal in the positioning coordinate system within the preset time period.

[0042] Preferably, the expression of the communication restriction condition is:

[0043] m i ≤M i0 -m i0

[0044] In the formula, m i is the total number of variable device terminals connected to the i-th server, M i0 is the maximum communication load of the ith server, m i0 is the total number of all device terminals accessing the i-th server except the changed device terminals.

[0045] Preferably, the calculation formula for the total communication switching index of all changed device terminals is:

[0046]

[0047] In the formula, Z b is the total communication switching index of all changed device terminals, B ij is the communication switching indicator between the i-th server and the j-th connected variable device terminal.

[0048] Furthermore, a multi-server communication switching system is proposed, which is used to implement the multi-server communication switching method as described above, including:

[0049] A regional analysis module, the regional analysis module is used to determine the best communication area for each server within the coverage of the multi-server communication network;

[0050] A trajectory prediction module, the trajectory prediction module is used to continuously and in real time acquire the location information of each device terminal, obtain the location change trajectory of each device terminal, and predict the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network within a preset time period based on the location change trajectory of each device terminal, which is recorded as predicted device terminal data;

[0051] A communication planning module, the communication planning module is electrically connected to the area analysis module and the trajectory prediction module, and the communication planning module is used to determine whether the predicted device terminal data of the optimal communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, all device terminals corresponding to the predicted device terminal data are connected to the corresponding server. If so, the communication server of each device terminal is adjusted based on the communication optimization algorithm.

[0052] Furthermore, a computer-readable storage medium is proposed, on which a computer-readable program is stored, and when the computer-readable program is called, the multi-server communication switching method as described above is executed.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention proposes a multi-server communication switching method, which predicts the user's behavior change trend based on the location change trajectory of the device terminal, and then dynamically predicts the user's location. Combined with the user's real-time predicted location and the communication load capacity between each server, the terminal-server communication scheme that maximizes the comprehensive communication stability of all users is dynamically adjusted, and the scheme is used to perform dynamic communication switching adjustment between the user and the server. Through this scheme, pre-prediction adjustment of server communication services is achieved, ensuring the stability of users when switching multi-server communications, thereby ensuring the stability of communication connections between users and multiple servers and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Flowchart of the multi-server communication switching method proposed for this solution;

[0056] Figure 2 This is a flow chart of the multi-server communication switching method in this solution;

[0057] Figure 3 A flow chart of a method for determining a stability index of a server in this solution;

[0058] Figure 4 This is a flow chart of the communication optimization algorithm method in this scheme. DETAILED DESCRIPTION

[0059] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0060] Reference Figure 1 As shown, a multi-server communication switching method includes:

[0061] Determine the best communication area for each server within the coverage of the multi-server communication network;

[0062] Determine the maximum communication load for each server;

[0063] Obtain all device terminals connected to the multi-server communication network;

[0064] Continuously obtain the location information of each device terminal in real time to obtain the location change trajectory of each device terminal;

[0065] Based on the position change trajectory of each device terminal, predict the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network within a preset time period, and record it as predicted device terminal data;

[0066] Determine whether the predicted device terminal data of the optimal communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, establish a communication connection between all device terminals corresponding to the predicted device terminal data and the corresponding server. If so, adjust the communication server of each device terminal based on the communication optimization algorithm.

[0067] This solution predicts the user's behavior change trend based on the location change trajectory of the device terminal, and then dynamically predicts the user's location. Combined with the user's real-time predicted location and the communication load capacity between each server, this solution dynamically adjusts the terminal-server communication solution that maximizes the comprehensive communication stability of all users. This solution also performs dynamic communication switching adjustments between users and servers to achieve pre-prediction adjustments to server communication services.

[0068] Reference Figure 2 As shown, the optimal communication area for each server within the coverage of the multi-server communication network is determined to specifically include:

[0069] Construct a positioning coordinate system within the coverage of the multi-server communication network;

[0070] Determine the physical location coordinates of each server in the positioning coordinate system;

[0071] Calculate the service communication index of each server at each location within the coverage of the multi-server communication network through a service communication index calculation formula;

[0072] Determine the server with the smallest service communication index at each location within the coverage of the multi-server communication network, and record the location as the best communication location for the server;

[0073] Determine the area consisting of all the best communication locations of each server, which is the best communication area of ​​the server;

[0074] Among them, the service communication indicator calculation formula is:

[0075]

[0076] Where, T i (x, y) is the service communication index of the i-th server for the position with coordinates (x, y) in the positioning coordinate system, Q i is the stability index of the i-th server, n is the total number of servers in the multi-server communication network, x i is the horizontal coordinate of the ith server in the positioning coordinate system, y i is the ordinate of the ith server in the positioning coordinate system, x is the abscissa of the position with coordinates (x, y) in the positioning coordinate system, and y is the ordinate of the position with coordinates (x, y) in the positioning coordinate system.

[0077] Reference Figure 3 As shown, the method for determining the stability index of the server is:

[0078] Determine the running status of the server and collect statistics on the running data of multiple servers of the same type in the same running status;

[0079] Based on the operating data of multiple servers of the same type under the same operating status, a logistics regression prediction model is constructed;

[0080] Based on the logistics regression prediction model, the probability of failure of the current server is determined and used as the stability indicator of the server;

[0081] The logistics regression prediction model is as follows:

[0082]

[0083] Where Q is the probability of server failure, T is the working time of the server, and α and β are the coefficients of the logistics regression prediction model.

[0084] It is understandable that the important indicators that affect the server communication service are the communication distance between the server and the device terminal and the operating stability of the server itself. The longer the communication distance between the server and the device terminal, the more communication node transfer nodes there are between the server and the device terminal, the greater the probability of communication problems, and the more unstable the communication service. The greater the probability of failure of the server itself, the more unstable its communication service. In this solution, the communication distance between the server and the device terminal and the operating stability of the server itself are combined to comprehensively screen out the servers that provide the best communication services for each location, and based on this, the best communication area of ​​each server is divided, which can realize the basic division of communication services within the coverage of the multi-server communication network.

[0085] Logistic regression, also known as logistic regression analysis, is a generalized linear regression analysis model, commonly used in the field of data prediction. Logistic regression estimates the probability of an event based on a given independent variable data set. Since the result is a probability, the range of the dependent variable is between 0 and 1. In this solution, a logistics regression prediction model is constructed to predict the regression relationship between the probability of server failure and working hours under the same operating state. In some other embodiments, other independent variable parameters can also be introduced for the prediction of server failure probability.

[0086] Reference Figure 4 As shown in Figure 2, the communication optimization algorithm is specifically as follows:

[0087] According to the position change trajectory of each device terminal, the device terminal whose optimal communication area changes within the preset time period is recorded as a changed device terminal;

[0088] For all other device terminals except the changed device terminal, the communication connection between the device terminal and the original server is maintained;

[0089] Based on the position change trajectory of the changing device terminal, the communication weight between the changing device terminal and each server is determined respectively;

[0090] Calculate the communication switching index between each changing device terminal and each server respectively;

[0091] Building communication restriction conditions based on the maximum communication load of each server and the device communication connection status of each server;

[0092] Determine the communication server corresponding to each variable device terminal under the condition of communication restriction so that the total communication switching index of all variable device terminals is minimized.

[0093] In some embodiments, based on the position change track of the changing device terminal, the communication weight between the changing device terminal and each server is determined as follows:

[0094] Adding a first communication weight to the server corresponding to the best communication area to which the changed device terminal moves, adding a second communication weight to the server corresponding to the initial best communication area where the changed device terminal is located, and adding a third communication weight to the remaining servers;

[0095] Among them, the first communication weight>the second communication weight>the third communication weight.

[0096] It can be understood that the server corresponding to the best communication area to which the changing device terminal moves is the server that provides the best communication service to the device terminal, and the server corresponding to the best communication area where the changing device terminal is initially located is the server that prevents the device terminal from performing communication switching, and its communication stability is the highest. Based on this, in this scheme, the server weights are divided into first communication weight, second communication weight and third communication weight, and relevant weight addition rules are set to add weight to each server. In some specific embodiments, the first communication weight is 1, the second communication weight is 0.8, and the third communication weight is 0.5.

[0097] The calculation formula for the communication switching index between the variable device terminal and each server is:

[0098]

[0099] In the formula, B i is the communication switching index between the i-th server and the changing device terminal, A i is the communication weight between the ith server and the changing device terminal, X is the horizontal coordinate of the changing device terminal in the positioning coordinate system within the preset time period, and Y is the vertical coordinate of the changing device terminal in the positioning coordinate system within the preset time period.

[0100] The expression of the communication constraint is:

[0101] m i ≤M i0 -m i0

[0102] In the formula, m i is the total number of variable device terminals connected to the i-th server, M i0 is the maximum communication load of the ith server, m i0 is the total number of all device terminals accessing the i-th server except the changed device terminals.

[0103] The calculation formula for the total communication switching index of all changed device terminals is:

[0104]

[0105] In the formula, Z b is the total communication switching index of all changed device terminals, B ij is the communication switching indicator between the i-th server and the j-th connected variable device terminal.

[0106] This solution builds communication switching indicators between servers and variable device terminals to dynamically represent the comprehensive evaluation indicators of switching smoothness and communication connection stability between each device terminal and each server when performing communication switching, and builds restriction conditions based on the load capacity of each server. Under the load capacity of each server, the communication switching plan of the device terminal is intelligently planned.

[0107] Based on the same inventive concept as the above-mentioned multi-server communication switching method, this solution proposes a multi-server communication switching system, including:

[0108] A regional analysis module, the regional analysis module is used to determine the best communication area for each server within the coverage of the multi-server communication network;

[0109] The trajectory prediction module is used to continuously and in real time obtain the location information of each device terminal, obtain the location change trajectory of each device terminal, and predict the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network based on the location change trajectory of each device terminal within a preset time period, which is recorded as predicted device terminal data;

[0110] The communication planning module is electrically connected to the regional analysis module and the trajectory prediction module. The communication planning module is used to determine whether the predicted device terminal data of the optimal communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, all device terminals corresponding to the predicted device terminal data are connected to the corresponding server. If so, the communication server of each device terminal is adjusted based on the communication optimization algorithm.

[0111] The working process of the above multi-server communication switching system is as follows:

[0112] Step 1: The regional analysis module constructs a positioning coordinate system within the coverage of the multi-server communication network; determines the physical location coordinates of each server in the positioning coordinate system; calculates the service communication index of each server at each location within the coverage of the multi-server communication network through the service communication index calculation formula; determines the server with the smallest service communication index at each location within the coverage of the multi-server communication network, and records the location as the best communication location of the server; determines the area composed of all the best communication locations of each server, which is the best communication area of ​​the server;

[0113] Step 2: The trajectory prediction module continuously obtains the location information of each device terminal in real time, obtains the location change trajectory of each device terminal, and predicts the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network based on the location change trajectory of each device terminal, which is recorded as predicted device terminal data;

[0114] Step 3: The communication planning module determines whether the predicted device terminal data of the optimal communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, all device terminals corresponding to the predicted device terminal data are connected to the corresponding server. If so, the device terminal whose optimal communication area changes within the preset time period is recorded as a changed device terminal according to the position change trajectory of each device terminal; for all device terminals except the changed device terminal, the communication connection between the device terminal and the original server is maintained; based on the position change trajectory of the changed device terminal, the communication weight between the changed device terminal and each server is determined respectively; the communication switching index between each changed device terminal and each server is calculated respectively; based on the maximum communication load of each server and the device communication connection status of each server, a communication restriction condition is constructed; and under the communication restriction condition, the communication server corresponding to each changed device terminal is determined so that the total communication switching index of all changed device terminals is minimized.

[0115] Furthermore, the present solution also proposes a computer-readable storage medium on which a computer-readable program is stored. When the computer-readable program is called, the multi-server communication switching method described above is executed.

[0116] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0117] In summary, the advantages of the present invention are: realizing pre-predictive adjustment of server communication services, ensuring the stability of users when switching between multiple servers, thereby ensuring the stability of communication connections between users and multiple servers, and improving user experience.

[0118] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A multi-server communication switching method, characterized in that: include: Determine the best communication area for each server within the coverage of the multi-server communication network; Determine the maximum communication load for each server; Obtain all device terminals connected to the multi-server communication network; Continuously obtain the location information of each device terminal in real time to obtain the location change trajectory of each device terminal; Based on the position change trajectory of each device terminal, predict the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network within a preset time period, and record it as predicted device terminal data; Determine whether the predicted device terminal data of the best communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, establish communication connections between all device terminals corresponding to the predicted device terminal data and the corresponding server. If yes, adjust the communication server of each device terminal based on the communication optimization algorithm. The communication optimization algorithm is specifically: According to the position change trajectory of each device terminal, the device terminal whose optimal communication area changes within the preset time period is recorded as a changed device terminal; For all other device terminals except the changed device terminal, the communication connection between the device terminal and the original server is maintained; Based on the position change trajectory of the changing device terminal, the communication weight between the changing device terminal and each server is determined respectively; Calculate the communication switching index between each changing device terminal and each server respectively; Building communication restriction conditions based on the maximum communication load of each server and the device communication connection status of each server; Determine the communication server corresponding to each changing device terminal under the condition of communication restriction so that the total communication switching index of all changing device terminals is minimized; The communication weight between the changing device terminal and each server is determined based on the position change trajectory of the changing device terminal as follows: Adding a first communication weight to the server corresponding to the best communication area to which the changed device terminal moves, adding a second communication weight to the server corresponding to the initial best communication area where the changed device terminal is located, and adding a third communication weight to the remaining servers; Among them, the first communication weight>the second communication weight>the third communication weight; The calculation formula of the communication switching index between the changing device terminal and each server is: In the formula, B i is the communication switching index between the i-th server and the changing device terminal, A i is the communication weight between the ith server and the changing device terminal, X is the horizontal coordinate of the changing device terminal in the positioning coordinate system within the preset time period, Y is the vertical coordinate of the changing device terminal in the positioning coordinate system within the preset time period, Q i is the stability index of the i-th server, n is the total number of servers in the multi-server communication network, x i is the horizontal coordinate of the ith server in the positioning coordinate system, y i is the vertical coordinate of the i-th server in the positioning coordinate system.

2. A multi-server communication switching method according to claim 1, characterized in that: The determination of the optimal communication area of ​​each server within the coverage of the multi-server communication network specifically includes: Construct a positioning coordinate system within the coverage of the multi-server communication network; Determine the physical location coordinates of each server in the positioning coordinate system; Calculate the service communication index of each server at each location within the coverage of the multi-server communication network through a service communication index calculation formula; Determine the server with the smallest service communication index at each location within the coverage of the multi-server communication network, and record the location as the best communication location for the server; Determine the area consisting of all the best communication locations of each server, which is the best communication area of ​​the server; The service communication indicator calculation formula is: Where, T i (x, y) is the service communication indicator of the i-th server for the position with coordinates (x, y) in the positioning coordinate system, x is the horizontal coordinate of the position with coordinates (x, y) in the positioning coordinate system, and y is the vertical coordinate of the position with coordinates (x, y) in the positioning coordinate system.

3. A multi-server communication switching method according to claim 2, characterized in that: The method for determining the stability index of the server is: Determine the running status of the server and collect statistics on the running data of multiple servers of the same type in the same running status; Based on the operating data of multiple servers of the same type under the same operating status, a logistics regression prediction model is constructed; Based on the logistics regression prediction model, the probability of failure of the current server is determined and used as the stability indicator of the server; The logistics regression prediction model is specifically: Where Q is the probability of server failure, T is the working time of the server, and α and β are the coefficients of the logistics regression prediction model.

4. A multi-server communication switching method according to claim 3, characterized in that: The expression of the communication restriction condition is: m i ≤M i0 -m i0 In the formula, m i is the total number of variable device terminals connected to the i-th server, M i0 is the maximum communication load of the ith server, m i0 is the total number of all device terminals accessing the i-th server except the changed device terminals.

5. A multi-server communication switching method according to claim 4, characterized in that: The calculation formula of the total communication switching index of all the changed device terminals is: In the formula, Z b is the total communication switching index of all changed device terminals, B ij is the communication switching indicator between the i-th server and the j-th connected variable device terminal.

6. A multi-server communication switching system, characterized in that: The method for implementing the multi-server communication switching method according to any one of claims 1 to 5 comprises: A regional analysis module, the regional analysis module is used to determine the best communication area for each server within the coverage of the multi-server communication network; A trajectory prediction module, the trajectory prediction module is used to continuously and in real time acquire the location information of each device terminal, obtain the location change trajectory of each device terminal, and predict the total number of device terminals at each time point in the optimal communication area of ​​each server within the coverage of the multi-server communication network within a preset time period based on the location change trajectory of each device terminal, which is recorded as predicted device terminal data; A communication planning module, the communication planning module is electrically connected to the area analysis module and the trajectory prediction module, and the communication planning module is used to determine whether the predicted device terminal data of the optimal communication area of ​​each server exceeds the maximum communication load of the corresponding server. If not, all device terminals corresponding to the predicted device terminal data are connected to the corresponding server. If so, the communication server of each device terminal is adjusted based on the communication optimization algorithm.

7. A computer-readable storage medium having a computer-readable program stored thereon, characterized in that: When the computer-readable program is called, the multi-server communication switching method as described in any one of claims 1-5 is executed.

Images