A data optimization management system and method for a network distribution model

Abstract

The present invention discloses a data optimization management system and method for a network distribution model, belonging to the technical field of artificial intelligence. The present invention includes the following steps: analyzing the comprehensive trend difference and traffic fluctuation value of the network to be managed at the same time point; establishing a traffic prediction model and training the traffic prediction model; obtaining the predicted traffic value of the network to be managed at the next time point; analyzing the server demand of the network to be managed at the next time point; adjusting the number of online servers of the network to be managed at the next time point; after adjusting the number of online servers of the network to be managed at the next time point, pre-distributing the load of each online server of the network to be managed at the next time point. By analyzing the historical traffic data of the network to be managed, the present invention balances the load of the servers, avoids the waste and overload of server resources, and greatly improves the stability and operation efficiency of the network.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a data optimization management system and method for a network distribution model. Background Art

[0002] A network distribution model refers to a method for managing and optimizing data flow, transmission, and resource allocation in a computer network. Its main purpose is to ensure the efficient distribution of data in the network, avoid network congestion, and improve the overall transmission efficiency.

[0003] In the modern Internet environment, as the complexity of user requirements and services continues to increase, network traffic has become increasingly volatile. The traditional resource allocation methods of servers often struggle to cope with this volatility, resulting in insufficient resources during peak traffic periods, causing server overload, and excessive resources during low traffic periods, resulting in resource waste, thus reducing the quality of network services and the utilization rate of resources.

[0004] Therefore, there is an urgent need for a data optimization management system for network distribution models to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a data optimization management system for a network distribution model to solve the problems raised in the above background art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] A data optimization management method for a network distribution model, the method comprising the following steps:

[0008] S1. Set a period, and collect the traffic values at each time point in different periods of the network to be managed; set a sliding window, calculate the traffic trends and trend differences at each time point in different periods of the network to be managed, and analyze the comprehensive trend difference and traffic fluctuation value at the same time point of the network to be managed.

[0009] S2. Establish a traffic prediction model and train the traffic prediction model; collect the traffic value at the current time point of the network to be managed, and obtain the predicted traffic value at the next time point of the network to be managed through the trained traffic prediction model.

[0010] S3. Collect the traffic processing capacity and maximum load utilization rate of the servers in the network to be managed, and analyze the server demand at the next time point of the network to be managed in combination with the predicted traffic value at the next time point of the network to be managed.

[0011] S4. Collect the number of online servers at the current time point of the network to be managed, and adjust the number of online servers at the next time point of the network to be managed.

[0012] S5. After adjusting the number of online servers at the next time point in the network to be managed, pre-allocate the loads of each online server at the next time point in the network to be managed.

[0013] According to the above technical solution, the specific process of step S1 is as follows:

[0014] S1-1. Set the period as T; denote the i-th time point as t i ; denote the traffic value at the i-th time point in the j-th period of the network to be managed as A j (t i );

[0015] S1-2. Set a sliding window, denoted as B k ; where k represents the size of the sliding window; calculate the traffic trend of each time point in different periods of the network to be managed according to the following formula:

[0016]

[0017] where C j (t i ) represents the traffic trend at the i-th time point in the j-th period of the network to be managed; A j (t a ) represents the traffic value within the sliding window B k at the i-th time point in the j-th period of the network to be managed; a represents the index for traversing time points in the sliding window B k , and a takes values from i - k + 1 to i in sequence;

[0018] The sliding window is a window with a fixed size, used for local analysis of time series data. The window moves step by step on the time series, moving one time step each time; capturing short-term trends through local time point data, eliminating noise, and at the same time smoothing traffic changes to help identify trends more accurately;

[0019] The traffic trend is used to identify the overall change direction in the time series. Through the trend, it can be known whether the traffic is increasing, decreasing, or remaining stable;

[0020] Calculate the trend difference of each time point in different periods of the network to be managed. The calculation formula is: ΔC j (t i ) = C j (t i ) - C j (t i-1 ); where ΔC j (t i ) represents the trend difference at the i-th time point in the j-th period of the network to be managed; C j (t i-1) represents the traffic trend at the i-th time point in the j-th cycle of the network to be managed; t i-1 represents the (i - 1)-th time point;

[0021] The trend difference is used to measure the change rate of the traffic trend. A positive difference indicates an increasing traffic trend, and a negative difference indicates a decreasing traffic trend;

[0022] Take the trend difference ΔC j (t i ) corresponding to the i-th time point in all cycles of the network to be managed, and calculate its average value as the comprehensive trend difference at the i-th time point of the network to be managed, denoted as ΔC1(t i );

[0023] S1 - 3. Take the traffic values A j (t i ) corresponding to all time points in the j-th cycle of the network to be managed, and calculate their average value as the average traffic value of the j-th cycle of the network to be managed, denoted as A1 j ;

[0024] Calculate the traffic fluctuation value at the same time point of the network to be managed according to the following formula:

[0025]

[0026] where D(t i ) represents the traffic fluctuation value at the i-th time point of the network to be managed;

[0027] The traffic fluctuation value is used to evaluate the stability of traffic at the same time point. A high fluctuation value indicates unstable traffic, and a low fluctuation value indicates relatively stable traffic.

[0028] According to the above technical solution, the specific process of step S2 is as follows:

[0029] S2 - 1. Establish a traffic prediction model as follows:

[0030] Y = X1 + α1×X2 + α2×X3 + α3;

[0031] where Y represents the dependent variable, X1, X2, and X3 all represent independent variables, α1 and α2 both represent adjustment parameters; α3 represents a correction parameter;

[0032] S2 - 2. Denote the (i + 1)-th time point as t i+1 ; Denote the traffic value at the (i + 1)-th time point in the j-th cycle of the network to be managed as A j (t i+1 );

[0033] S2 - 3. For the traffic values A corresponding to the (i + 1)-th time point in each cycle of the network to be managedj (t i+1 ), as the corresponding Y in the training set; take the traffic value A corresponding to the i-th time point in each cycle of the network to be managed j (t i ), as the corresponding X1 in the training set; take the comprehensive trend difference ΔC1(t corresponding to the i-th time point of the network to be managed i ), as the corresponding X2 in the training set; take the traffic fluctuation value D(t corresponding to the i-th time point of the network to be managed i ), as the corresponding X3 in the training set; train the traffic prediction model through the training set;

[0034] S2-4: Denote the current time point as t; denote the next time point as t + 1; denote the traffic value of the network to be managed at the current time point as F t ; Take F t , and through the trained traffic prediction model, obtain the predicted traffic value of the network to be managed at the next time point, denoted as F t+1 .

[0035] According to the above technical solution, the specific process of step S3 is as follows:

[0036] Denote the traffic processing capacity of the servers in the network to be managed as G; denote the maximum load utilization rate of the servers in the network to be managed as H; calculate the server demand of the network to be managed at the next time point according to the following formula:

[0037]

[0038] where N t+1 represents the server demand of the network to be managed at the next time point; represents rounding up the value of F t+1 / (G·H);

[0039] The traffic processing capacity refers to the maximum amount of network traffic that a server can process per unit time, which can be directly measured using a network performance testing tool.

[0040] According to the above technical solution, the specific process of step S4 is as follows:

[0041] S4-1: Denote the number of online servers at the current time point of the network to be managed as N t ;

[0042] S4-2: If N t+1 ≥N t , it means that the number of online servers is insufficient when processing the traffic at the next time point, and online servers need to be added at the next time point. The increased number is (N t+1 -N t);

[0043] If N t+1 <N t , it means that the number of online servers of the online server is sufficient when processing the traffic at the next time point, and the number of online servers needs to be reduced at the next time point. The reduced number is (N t -N t+1 ).

[0044] According to the above technical solution, the specific process of the step S5 is as follows:

[0045] After adjusting the number of online servers of the network to be managed at the next time point, the number of online servers of the network to be managed at the next time point is N t+1 , and pre-allocate the loads of each online server of the network to be managed at the next time point, so that the loads of each online server should meet the following conditions: I b，t+1 ≤I = F t+1 / N t+1 ; where I b，t+1 represents the load of the bth online server of the network to be managed at the next time point; I represents the predicted average traffic value of the network to be managed at the next time point.

[0046] A data optimization management system for a network distribution model, the system includes an information collection module, an information processing module and an execution module;

[0047] The information collection module is used to collect the information required by the system; the information processing module is used to store, analyze and transmit the information of each module; the execution module is used to execute the information of the information processing module.

[0048] According to the above technical solution, the information collection module includes a historical information unit and a real-time information unit;

[0049] The historical information unit is used to collect the historical data information of the traffic and servers in the network to be managed, and the real-time information unit is used to collect the real-time data information of the traffic and servers in the network to be managed.

[0050] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0051] The information storage unit is used to store the information obtained by the information collection module; the information analysis unit is used to analyze the information obtained by the information collection module; the information transmission unit is used for information transmission among the various modules in the system.

[0052] According to the above technical solution, the execution module includes a suggestion display unit and a regulation unit;

[0053] The display unit is used to display the data information of the traffic and online servers in the network to be managed; the regulation unit is used to regulate the servers in the network to be managed.

[0054] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0055] By analyzing the historical traffic data of the network to be managed, the present invention obtains the trend and difference of the historical traffic data, can capture the traffic fluctuation law more accurately, and improves the accuracy of traffic prediction; on this basis, the traffic of the network to be managed is predicted to ensure the accurate analysis of the server demand, and the change of network traffic is more effectively responded to; by dynamically adjusting the number of online servers and pre-distributing the load of the online servers, the load of the servers is balanced, and the waste and overload of server resources are avoided, greatly improving the stability and operation efficiency of the network. Description of the Drawings

[0056] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0057] Figure 1 is a schematic flow chart of a data optimization management method for a network distribution model of the present invention;

[0058] Figure 2 is a schematic structural diagram of a data optimization management system for a network distribution model of the present invention. Detailed Embodiments

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0060] Please refer to Figure 1 , the present invention provides the following technical solutions:

[0061] A data optimization management method for a network distribution model, the method includes the following steps:

[0062] S1. Set a period, and collect the traffic values at each time point in different periods of the network to be managed; set a sliding window, calculate the traffic trend and trend difference at each time point in different periods of the network to be managed, and analyze the comprehensive trend difference and traffic fluctuation value at the same time point of the network to be managed;

[0063] According to the above technical solution, the specific process of step S1 is as follows:

[0064] S1-1. Set the period as T; denote the i-th time point as t i ; denote the traffic value at the i-th time point in the j-th period of the network to be managed as A j (t i );

[0065] For example:

[0066] Set the period T = 1 day, and the time points are the 24 time points of 1 day;

[0067] S1-2. Set a sliding window, denoted as B k ; where k represents the size of the sliding window; calculate the traffic trend of each time point in different periods of the network to be managed according to the following formula:

[0068]

[0069] where C j (t i ) represents the traffic trend at the i-th time point in the j-th period of the network to be managed; A j (t a ) represents the traffic value of the i-th time point in the j-th period of the network to be managed within the sliding window B k ; a represents the index for traversing time points in the sliding window B k , and a takes values from i - k + 1 to i in sequence;

[0070] For example:

[0071] Given that k = 3, A j (t i＝14 ) = 140, A j (t i＝15 ) = 150, A j (t i＝16 ) = 160, according to the formula:

[0072]

[0073] Obtain the traffic trend C j (t i＝16 ) = 150 at the i = 16-th time point in the j-th period of the network to be managed;

[0074] The sliding window is a window with a fixed size, used for local analysis of time series data. The window moves step by step on the time series, moving one time step each time; capturing short-term trends through local time point data, eliminating noise, and at the same time smoothing traffic changes to help identify trends more accurately;

[0075] Flow trends are used to identify the overall direction of change in a time series. Through trends, it can be understood whether the flow is increasing, decreasing, or remaining stable;

[0076] Calculate the trend difference at each time point in different cycles of the network to be managed. The calculation formula is: ΔC j (t i ) = C j (t i ) - C j (t i-1 ) ; where, ΔC j (t i ) represents the trend difference at the i-th time point in the j-th cycle of the network to be managed; C j (t i-1 ) represents the flow trend at the i-th time point in the j-th cycle of the network to be managed; t i-1 represents the (i - 1)-th time point;

[0077] The trend difference is used to measure the change rate of the flow trend. A positive difference indicates that the flow trend is rising, and a negative difference indicates that the flow trend is falling;

[0078] Take the average value of the trend differences ΔC j (t i ) corresponding to the i-th time point in all cycles of the network to be managed as the comprehensive trend difference at the i-th time point of the network to be managed, denoted as ΔC1(t i ) ;

[0079] S1 - 3. Take the average value of the flow values A j (t i ) corresponding to all time points in the j-th cycle of the network to be managed as the average flow value in the j-th cycle of the network to be managed, denoted as A1 j ;

[0080] Calculate the flow fluctuation value at the same time point of the network to be managed according to the following formula:

[0081]

[0082] where, D(t i ) represents the flow fluctuation value at the i-th time point of the network to be managed;

[0083] The flow fluctuation value is used to evaluate the stability of the flow at the same time point. A high fluctuation value indicates that the flow is unstable, and a low fluctuation value indicates that the flow is relatively stable.

[0084] S2. Establish a flow prediction model and train the flow prediction model; collect the flow value at the current time point of the network to be managed, and obtain the predicted flow value at the next time point of the network to be managed through the trained flow prediction model;

[0085] According to the above technical solution, the specific process of step S2 is as follows:

[0086] S2-1. Establish a traffic prediction model as follows:

[0087] Y = X1 + α1×X2 + α2×X3 + α3;

[0088] Wherein, Y represents the dependent variable, X1, X2, and X3 all represent independent variables, α1 and α2 both represent adjustment parameters; α3 represents a correction parameter;

[0089] S2-2. Denote the (i + 1)-th time point as t i+1 ; Denote the traffic value at the (i + 1)-th time point in the j-th cycle of the network to be managed as A j (t i+1 );

[0090] S2-3. Use the traffic value A j (t i+1 ) corresponding to the (i + 1)-th time point in each cycle of the network to be managed as the corresponding Y in the training set; use the traffic value A j (t i ) corresponding to the i-th time point in each cycle of the network to be managed as the corresponding X1 in the training set; use the comprehensive trend difference ΔC1(t i ) corresponding to the i-th time point of the network to be managed as the corresponding X2 in the training set; use the traffic fluctuation value D(t i ) corresponding to the i-th time point of the network to be managed as the corresponding X3 in the training set; train the traffic prediction model through the training set;

[0091] S2-4. Denote the current time point as t; denote the next time point as t + 1; denote the traffic value of the network to be managed at the current time point as F t ; Use F t , through the trained traffic prediction model, to obtain the predicted traffic value of the network to be managed at the next time point, denoted as F t+1 ;

[0092] For example:

[0093] It is known that the current time point t = t i＝16 , the traffic value F t of the network to be managed at the current time point = 160, the trend difference ΔC1(t i＝16 ) corresponding to the i = 16-th time point in all cycles of the network to be managed = 5, the traffic fluctuation value D(t i＝16) = 10, α1 = 0.5, α2 = 0.3, α3 = -0.2 in the traffic prediction model; according to the traffic prediction model, obtain the predicted traffic value F at the next time point of the network to be managed t+1 =(F t = 160)+(α1 = 0.5)×(ΔC1(t i＝16 ) = 5)+(α2 = 0.3)×(D(t i＝16 ) = 10)+(α3 = -0.2) = 163.8.

[0094] S3. Collect the traffic processing capacity and maximum load utilization rate of the servers in the network to be managed, and combine with the predicted traffic value at the next time point of the network to be managed to analyze the server demand at the next time point of the network to be managed;

[0095] According to the above technical solution, the specific process of step S3 is as follows:

[0096] Denote the traffic processing capacity of the servers in the network to be managed as G; denote the maximum load utilization rate of the servers in the network to be managed as H; calculate the server demand at the next time point of the network to be managed according to the following formula:

[0097]

[0098] where N t+1 represents the server demand at the next time point of the network to be managed; represents rounding up the value of F t+1 / (G·H);

[0099] For example:

[0100] It is known that the traffic processing capacity G of the servers in the network to be managed = 50; the maximum load utilization rate H of the servers in the network to be managed = 0.8; the predicted traffic value F at the next time point of the network to be managed t+1 = 163.8; calculate the server demand at the next time point of the network to be managed according to the following formula:

[0101]

[0102] Obtain the server demand N at the next time point of the network to be managed t+1 = 5;

[0103] The traffic processing capacity refers to the maximum amount of network traffic that a server can process per unit time, and can be directly measured using a network performance testing tool.

[0104] S4. Collect the number of online servers at the current time point of the network to be managed and adjust the number of online servers at the next time point of the network to be managed;

[0105] According to the above technical solution, the specific process of step S4 is as follows:

[0106] S4-1. Denote the number of online servers at the current time point of the network to be managed as N t ;

[0107] S4-2. If N t+1 ≥N t , it means that the number of online servers is insufficient when processing the traffic at the next time point, and online servers need to be added at the next time point. The number of added servers is (N t+1 -N t );

[0108] If N t+1 <N t , it means that the number of online servers is sufficient when processing the traffic at the next time point, and online servers need to be reduced at the next time point. The number of reduced servers is (N t -N t+1 ).

[0109] S5. After adjusting the number of online servers at the next time point of the network to be managed, pre-allocate the loads of each online server at the next time point of the network to be managed;

[0110] According to the above technical solution, the specific process of step S5 is as follows:

[0111] After adjusting the number of online servers at the next time point of the network to be managed, the number of online servers at the next time point of the network to be managed is N t+1 , and pre-allocate the loads of each online server at the next time point of the network to be managed so that the loads of each online server should meet the following conditions: I b，t+1 ≤I = F t+1 / N t+1 ; where I b，t+1 represents the load of the b-th online server at the next time point of the network to be managed; I represents the predicted average traffic value at the next time point of the network to be managed.

[0112] Please refer to Figure 2 , a data optimization management system for a network distribution model. The system includes an information collection module, an information processing module, and an execution module;

[0113] The information collection module is used to collect the information required by the system; the information processing module is used to store, analyze, and transmit the information of each module; the execution module is used to execute the information of the information processing module.

[0114] According to the above technical solution, the information collection module includes a historical information unit and a real-time information unit;

[0115] The historical information unit is used to collect historical data information of traffic and servers in the network to be managed, and the real-time information unit is used to collect real-time data information of traffic and servers in the network to be managed.

[0116] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit, and an information transmission unit;

[0117] The information storage unit is used to store the information obtained by the information collection module; the information analysis unit is used to analyze the information obtained by the information collection module; the information transmission unit is used for information transmission among various modules in the system.

[0118] According to the above technical solution, the execution module includes a suggestion display unit and a regulation unit;

[0119] The display unit is used to display data information of traffic and online servers in the network to be managed; the regulation unit is used to regulate the servers in the network to be managed.

[0120] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A data optimization management method for a network distribution model, characterized in that: The method comprises the following steps: S1. Set a cycle to collect traffic values ​​at each time point in different cycles of the network to be managed; set a sliding window to calculate the traffic trend and trend difference at each time point in different cycles of the network to be managed, and analyze the comprehensive trend difference and traffic fluctuation value at the same time point of the network to be managed; S2. Establish a traffic prediction model and train the traffic prediction model; collect the traffic value of the network to be managed at the current time point, and obtain the predicted traffic value of the network to be managed at the next time point through the trained traffic prediction model; S3, collecting the traffic processing capacity and maximum load utilization of the servers in the managed network, combining the predicted traffic value of the managed network at the next time point, and analyzing the server demand of the managed network at the next time point; S4, collecting the number of online servers at the current time point of the network to be managed, and adjusting the number of online servers at the next time point of the network to be managed; S5. After adjusting the number of online servers of the managed network at the next time point, pre-allocate the load of each online server of the managed network at the next time point; The specific process of step S1 is as follows: S1-1, set the period to T; record the i-th time point as t i ; The traffic value at the i-th time point in the j-th cycle of the managed network is recorded as A j (t i ); S1-2, set the sliding window, denoted as B k ; Where k represents the size of the sliding window; the traffic trend at each time point in different cycles of the managed network is calculated according to the following formula: ； Among them, C j (t i ) represents the traffic trend at the i-th time point in the j-th cycle of the managed network; A j (t a ) indicates that the i-th time point in the j-th cycle of the managed network is located in the sliding window B k The flow value within; a represents the sliding window B k In is used to traverse the index of time points, a takes values ​​from i-k+1 to i in sequence; Calculate the trend difference at each time point in different cycles of the managed network. The calculation formula is: ΔC j (t i )=C j (t i )-C j (t i-1 ); where ΔC j (t i ) represents the trend difference at the i-th time point in the j-th cycle of the network to be managed; C j (t i-1 ) represents the traffic trend at the i-th time point in the j-th cycle of the managed network; t i-1 represents the i-1th time point; Take the trend difference ΔC corresponding to the i-th time point in all cycles of the network to be managed j (t i ) is taken as the comprehensive trend difference of the network to be managed at the i-th time point, and is recorded as ΔC1 (t i ); S1-3. Get the traffic value A corresponding to all time points in the jth cycle of the network to be managed j (t i ) is taken as the average flow value of the jth period of the network to be managed, and is recorded as A1 j ; The traffic fluctuation value of the network to be managed at the same time point is calculated according to the following formula: ； Among them, D (t i ) represents the traffic fluctuation value of the network to be managed at the i-th time point; The specific process of step S3 is as follows: The traffic processing capacity of the server in the managed network is recorded as G; the maximum load utilization rate of the server in the managed network is recorded as H; the server demand of the managed network at the next time point is calculated according to the following formula: ； Among them, N t+1 Indicates the server demand at the next time point of the network to be managed; Express The value of is rounded up.

2. The data optimization management method for a network distribution model according to claim 1, characterized in that: The specific process of step S2 is as follows: S2-1. Establish a traffic prediction model, as follows: Y = X1 + α1 × X2 + α2 × X3 + α3; Among them, Y represents the dependent variable, X1, X2 and X3 all represent the dependent variables, α1 and α2 both represent the adjustment parameters; α3 represents the correction parameter; S2-2, let the i+1th time point be t i+1 ; The traffic value at the i+1th time point in the jth cycle of the managed network is recorded as A j (t i+1 ); S2-3, the flow value A corresponding to the i+1th time point in each cycle of the network to be managed j (t i+1 ), as the corresponding Y in the training set; the flow value A corresponding to the i-th time point in each cycle of the network to be managed j (t i ), as the corresponding X1 in the training set; the comprehensive trend difference ΔC1 (t i ), as the corresponding X2 in the training set; the traffic fluctuation value D (t i ), as the corresponding X3 in the training set; the traffic prediction model is trained through the training set; S2-4, record the current time point as t; record the next time point as t+1; record the flow value of the network to be managed at the current time point as F t ; F t , through the trained traffic prediction model, the predicted traffic value of the network to be managed at the next time point is obtained, which is recorded as F t+1 .

3. The data optimization management method for a network distribution model according to claim 2, characterized in that: The specific process of step S4 is as follows: S4-1. The number of online servers at the current time point in the managed network is recorded as N t ; S4-2, if N t+1 ≥N t , indicating that the number of online servers is insufficient to handle the traffic at the next time point, and additional online servers are needed at the next time point. The number of additional servers is (N t+1 -N t ); If N t+1 <N t , indicating that the number of online servers is sufficient to handle the traffic at the next time point, and the number of online servers to be reduced at the next time point is (N t -N t+1 ).

4. The data optimization management method for a network distribution model according to claim 3, characterized in that: The specific process of step S5 is as follows: After adjusting the number of online servers in the managed network at the next time point, the number of online servers in the managed network at the next time point is N t+1 , pre-allocate the load of each online server at the next time point in the managed network, so that the load of each online server should meet the following conditions: I b，t+1 ≤I=F t+1 / N t+1 ; Among them, I b，t+1 represents the load of the bth online server of the managed network at the next time point; I represents the predicted average traffic value of the managed network at the next time point.

5. A data optimization management system for a network distribution model, such as a data optimization management method for a network distribution model according to any one of claims 1 to 4, characterized in that: The system includes an information collection module, an information processing module and an execution module; The information acquisition module is used to acquire the information required by the system; the information processing module is used to store, analyze and transmit the information of each module; and the execution module is used to execute the information of the information processing module.

6. A data optimization management system for a network distribution model according to claim 5, characterized in that: The information collection module includes a historical information unit and a real-time information unit; The historical information unit is used to collect historical data information of traffic and servers in the network to be managed, and the real-time information unit is used to collect real-time data information of traffic and servers in the network to be managed.

7. The data optimization management system for network distribution model according to claim 5, characterized in that: The information processing module includes an information storage unit, an information analysis unit and an information transmission unit; The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission of each module in the system.

8. The data optimization management system for network distribution model according to claim 5, characterized in that: The execution module includes a suggestion display unit and a control unit; The display unit is used to display the data information of the traffic and online servers in the network to be managed; the control unit is used to control the servers in the network to be managed.

Images