Traffic control server, method, and system based on impact degree calculation using metric information

Abstract

The present disclosure may be characterized by controlling a service server to: calculate an impact degree on metric information on the basis of the number of access requests for each API group and the metric information of users' terminals received from the service server through a communication unit; output change information of the metric information on the basis of the number of access requests for each API group and the impact degree; extract a preset target traffic processing number for each API group linked to the change information of the metric information; and perform traffic control on the basis of the target traffic processing number for each API group.

Description

Traffic control server, method, and system based on impact calculation using metric information

[0001] The present disclosure relates to a traffic control server, method and system based on impact calculation using metric information.

[0002] As the number of simultaneous users accessing the service server providing content services such as course registration, concert reservations, and purchase events increases, the response speed of the service server providing the content services is often reduced or the service is interrupted.

[0003] The system may be composed of a WEB that provides web pages composed of HTML (hypertext markup language), a WAS (web application server) that processes application services for request messages transmitted from the WEB, and an information base that stores information that can be provided in response to queries.

[0004] In the above-described system, if there is a surge in concurrent users, the WEB may experience a surge in traffic due to insufficient network bandwidth.

[0005] Recently, research has been continuously conducted on technologies to efficiently control traffic in traffic-generating sections and allow targets to enter efficiently.

[0006] The purpose of the embodiment disclosed in the present disclosure is to provide a method for efficiently controlling traffic in a traffic generation section to allow an entry target to enter efficiently.

[0007] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0008] According to one embodiment of the present disclosure for achieving the above-described technical task, a traffic control server based on influence calculation using metric information comprises: a communication unit for performing communication with terminals of users attempting to enter a service server; a memory for storing at least one process related to control of traffic based on influence calculation using metric information; And a processor for performing an operation according to the process, wherein the processor calculates an influence on the metric information based on the number of connection requests for each API group of the user's terminals received from the service server through the communication unit and the metric information, outputs change information of the metric information based on the number of connection requests for each API group and the influence, extracts a target traffic processing number for each API group that is set in advance in connection with the change information of the metric information, and controls the service server to perform control of the traffic based on the target traffic processing number for each API group, wherein when extracting the target traffic processing number for each API group, if the degree of change in the metric information is higher than a preset level, the number of connection requests for a first API group and the number of connection requests for a second API group are compared, and when extracting the target traffic processing number for each API group, if the number of connection requests for the first API group is greater than the number of connection requests for the second API group, the first target traffic processing number for the first API group that is set in advance to be less than the number of connection requests for the first API group in order to reduce the traffic can be extracted.

[0009] In addition, a traffic control system based on impact calculation using metric information according to an embodiment of the present disclosure for achieving the above-described technical task includes: a service server providing a content service; terminals of users attempting to enter the service server; And a traffic control server that performs communication with the service server and the user's terminals, wherein the traffic control server calculates an influence on the metric information based on the number of connection requests and metric information for each API group of the user's terminals received from the service server, outputs change information of the metric information based on the number of connection requests and the influence for each API group, extracts a target traffic processing number for each API group that is set in advance in connection with the change information of the metric information, and controls the service server to perform control of the traffic based on the target traffic processing number for each API group, wherein when extracting the target traffic processing number for each API group, if the degree of change in the metric information is higher than a preset level, the number of connection requests for a first API group and the number of connection requests for a second API group are compared, and when extracting the target traffic processing number for each API group, if the number of connection requests for the first API group is greater than the number of connection requests for the second API group, the first target traffic processing number for the first API group that is set in advance to be less than the number of connection requests for the first API group in order to reduce the traffic can be extracted.

[0010] In addition, a computer program stored in a computer-readable recording medium for executing the present disclosure may be further provided.

[0011] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0012] According to the aforementioned problem solving means of the present disclosure, it provides an effect of efficiently controlling traffic in a traffic generation section, thereby efficiently allowing an entry target to enter.

[0013] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0014] FIG. 1 is a diagram illustrating a traffic control system based on impact calculation using metric information according to the present disclosure.

[0015] Figure 2 is a diagram showing the configuration of the traffic control server of Figure 1.

[0016] Figures 3 to 14 are drawings showing examples of a traffic control process based on calculating influence using metric information according to the present disclosure.

[0017] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0018] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0019] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0020] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0021] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0022] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0023] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0024] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0025] The traffic control server according to the present disclosure herein includes various devices capable of performing computational processing and providing results to a user. For example, the traffic control server according to the present disclosure may include a computer, a server device, and a mobile terminal, or may be any one of them.

[0026] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0027] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, an information base server, a file server, a proxy server, and a web server.

[0028] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0029] The traffic control system based on impact calculation using metric information according to the present disclosure calculates the impact on metric information based on the number of connection requests and metric information for each API group of user terminals received from the service server through the communication unit, outputs change information of metric information based on the number of connection requests and influence for each API group, extracts a target traffic processing number for each API group set in connection with the change information of metric information, and controls the service server to perform traffic control based on the target traffic processing number for each API group.

[0030] This traffic control system based on impact calculation using metric information can efficiently control traffic in the traffic generation section and allow the target to enter efficiently.

[0031] Below, we will examine in detail a traffic control system based on impact calculation using metric information.

[0032] FIG. 1 is a diagram illustrating a traffic control system based on impact calculation using metric information according to the present disclosure.

[0033] Referring to FIG. 1, a traffic control system (1000) may include a traffic control server (100), a user terminal (End-User (Browser), 200), and a service server (300).

[0034] The traffic control server (100) is located between the user's terminal (End-User (Browser)) (200) and the service server (300), and can efficiently control traffic in the traffic generation section to efficiently manage the user's terminal's (200) access to the service server (300). At this time, the user's terminal (200) may be multiple, and may be an end-user's terminal. The end-user disclosed below may have the same meaning as the user's terminal (200).

[0035] Additionally, the traffic control server (100) can perform procedures for blocking, bypassing, and allowing entry to a user's terminal (200) requesting entry to the service server (300).

[0036] The above blocking may mean a procedure for transmitting blocking information to the user's terminal (200) to prevent the selection of a button that causes a specific action (e.g., submit and confirm) when the number of accesses per second is at a macro level (e.g., N clicks per second, etc.).

[0037] The above-mentioned bypass may mean a procedure for bypassing a queue to enter the service server (300) and entering directly into the service server (300) without waiting in the queue in the case of a specific policy or major client.

[0038] The above entry permission management refers to normal waiting management for entry to the service server (300), and may refer to a procedure for managing resources or status of the service server (300) that provides content services by controlling entry based on the number of entry permissions.

[0039] At this time, the number of allowed entries may refer to the number of users who can simultaneously enter a specific transaction (e.g., login button, course registration button, etc.) of the service server (300) at the given time by receiving a key from the entry management server (100). At this time, the number of users may refer to the number of user terminals that can actually enter the service server (300) through the user terminal (200).

[0040] The service server (300) may include a web server (310), a web application server (WAS) server (320), and a database server (330). At this time, the service server (300) may provide various content services (first-come, first-served draws, course registration, concert reservations, accommodation reservations, ticket reservations, transportation reservations, etc.). Here, the service server (300) may include service server information. At this time, the service server information may be information collected from an application performance management (APM) that monitors the web application server (WAS) of the service server (300). Specifically, the service server information may include at least one of CPU information, memory information, disk information, network information, throughput, number of threads, response time, concurrent terminal users, active services, active users, error rate, rejection rate, number of hits per hour, number of visitors per hour, number of hits per day, number of visitors per day, user company WAS status, JDBC (java database connectivity) idleness, JDBC allocation, JDBC activity, total JVM (java virtual machine) memory, and JVM memory usage.

[0041] A WEB server (310) refers to a server that mainly processes requests from clients such as web browsers or web crawlers based on the HTTP (hypertext transfer protocol) protocol, and can reply with an HTTP response when an HTTP request is received.

[0042] For example, the WEB server (310) can receive a file path name and return static file content (html, jpeg, css, etc.) that matches the path.

[0043] The WEB server (310) can transmit a request for providing dynamic content to the WAS, receive the processing result from the WAS server (320), and transmit it to the client.

[0044] The WAS server (320) refers to an application server using HTTP, and may include a container that enables dynamic information to be used in a web server specialized in processing static HTTP information.

[0045] The WAS server (320) may be an application server for providing dynamic content requiring information base queries or various logic processing. The WAS server (320) may be middleware (software engine) that executes applications on a computer or device via HTTP. The WAS server (320) may also be referred to as a web container or servlet container. In this case, the container may refer to software capable of executing JSP and Servlet.

[0046] The WAS server (320) can be applied in a distributed environment that handles functions such as distributed transactions, security, messaging, and thread processing.

[0047] Specifically, the WAS server (320) can implement a program execution environment, an information base connection function, and a number of transaction management functions. The transaction may refer to a logical work unit.

[0048] The WAS server (320) can receive information from the DB server (330) at the user's request, generate results in real time according to the business logic, and provide them. The WAS server (320) can be implemented in multiple units, and the number of WAS servers (320) applied to each service server (300) can be different.

[0049] The DB server (330) may refer to a configuration that stores and manages information. At this time, the DB server (330) may respond to the request of the WAS server (320).

[0050] Figure 2 is a diagram showing the configuration of the traffic control server of Figure 1.

[0051] Referring to FIG. 2, the traffic control server (100) may include a processor (110), a memory (120), and a communication unit (130).

[0052] First, the communication unit (130) can communicate with the user's terminals (200) and the service server (300). Here, the communication unit (130) can communicate with the service server (300) and the user's terminals (200) requesting access to the service server (300). At this time, the communication unit (130) can include at least one of a wired communication module and a wireless communication module.

[0053] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0054] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0055] The memory (120) can store information about an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm. The processor (110) can communicate with the memory (120) and perform the aforementioned operations using the information stored in the memory (120). Here, the processor (110) and the memory (120) can be implemented as separate chips. Alternatively, the processor (110) and the memory (120) can be implemented as a single chip.

[0056] The memory (120) can store information supporting various functions of the device, programs for the operation of components within the device, input / output information, and a plurality of application programs (or applications) run on the device, information for the operation of the device, and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0057] The memory (120) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk.

[0058] The memory (120) can store at least one process related to controlling traffic based on impact calculation using metric information. The processor (110) can perform operations according to the process related to controlling traffic based on impact calculation using metric information.

[0059] The processor (110) can calculate the impact on the metric information based on the number of connection requests and metric information per API group of the user's terminals (200) received from the service server (300) through the communication unit (130).

[0060] Here, the processor (110) can calculate the influence on the metric information based on the number of connection requests of the first API group and the number of connection requests of the second API group among the number of connection requests by API group, and the CPU information, memory information, disk information, and network information included in the metric information.

[0061] At this time, the processor (110) can calculate the influence on the metric information by using the equation of a straight line based on the normal vector of the number of connection requests of the first API group, the number of connection requests of the second API group, and at least one of CPU information, memory information, disk information, and network information.

[0062] The processor (110) can output change information in metric information based on the number of access requests and influence per API group. At this time, the processor (110) can extract a target traffic processing number for each API group set in advance in connection with the change information in metric information, and control the service server (300) to perform traffic control based on the target traffic processing number for each API group.

[0063] For example, when extracting the number of target traffic processed by API group, the processor (110) may further compare the number of connection requests of the first API group and the number of connection requests of the second API group if the change in metric information is higher than a preset level.

[0064] At this time, if the number of connection requests of the first API group is greater than the number of connection requests of the second API group, the processor (110) may further extract the first target traffic processing number of the first API group, which is preset to be smaller than the number of connection requests of the first API group, in order to reduce traffic.

[0065] Additionally, if the number of connection requests of the second API group is greater than the number of connection requests of the first API group, the processor (110) may further extract a second target traffic processing number of the second API group, which is preset to be less than the number of connection requests of the second API group, in order to reduce traffic.

[0066] As another example, when extracting the target traffic processing number by API group, if the change in metric information is higher than a preset level, the processor (110) may further compare the average usage time of the first content service linked to the number of connection requests of the first API group and the average usage time of the second content service linked to the number of connection requests of the second API group.

[0067] At this time, if the average usage time of the first content service is greater than the average usage time of the second content service, the processor (110) may further extract the third target traffic processing number of the preset first API group to reduce traffic.

[0068] Additionally, if the average usage time of the second content service is greater than the average usage time of the first content service, the processor (110) may further extract the fourth target traffic processing number of the preset second API group to reduce traffic.

[0069] As another example, when extracting the target traffic processing number by API group, if the change in metric information is higher than a preset level, the processor (110) may further compare the average usage ranking of the first content service linked to the number of connection requests of the first API group and the average usage ranking of the second content service linked to the number of connection requests of the second API group.

[0070] At this time, if the average usage ranking of the first content service is faster than the average usage ranking of the second content service, the processor (110) may further extract the fifth target traffic processing number of the preset first API group to reduce traffic.

[0071] Additionally, if the average usage ranking of the second content service is faster than the average usage ranking of the first content service, the processor (110) may further extract the sixth target traffic processing number of the preset second API group to reduce traffic.

[0072] As another example, when extracting the target traffic processing number for each API group, if the change in metric information is higher than a preset level, the processor (110) may further compare the processing speed of the first content service linked to the number of connection requests of the first API group and the processing speed of the second content service linked to the number of connection requests of the second API group.

[0073] At this time, if the processing speed of the first content service is slower than the processing speed of the second content service, the processor (110) may further extract the seventh target traffic processing number of the preset first API group to reduce traffic.

[0074] Additionally, if the processing speed of the second content service is slower than the processing speed of the first content service, the processor (110) may further extract the eighth target traffic processing number of the preset second API group to reduce traffic.

[0075] Figures 3 to 14 are drawings showing examples of a traffic control process based on calculating influence using metric information according to the present disclosure.

[0076] Referring to FIGS. 3 to 14, a traffic control method based on calculating influence using metric information may include a receiving step (S310), a calculating step (S320), an output step (S330), an extraction step (S340), and a control step (S350).

[0077] The communication unit (130) can receive the number of connection requests and metric information for each API group of the user's terminals (200) from the service server (300) (S310). At this time, as illustrated in FIG. 4, the communication unit (130) can receive the number of connection requests for the first API group (210), the number of connection requests for the second API group (220), and metric information. Here, the API (Application Programming Interface) may be a series of rules or protocols that enable software applications to communicate with each other and exchange data, features, and functions.

[0078] Here, "metric" information refers to information that changes over time and may include CPU, memory, disk, and network information. Metric information may be valuable for tracking trends over time, such as CPU usage, CPU status, memory usage, memory status, disk I / O usage, disk status, network usage, and network status.

[0079] The processor (110) can calculate the impact on metric information based on the number of connection requests per API group of the user's terminals (200) and metric information (S320). In this case, the impact refers to the extent to which the service server (300) processing the connection requests per API group of the user's terminals (200) is using resources.

[0080] Here, the processor (110) can calculate the influence on the metric information based on the number of connection requests of the first API group (210) and the number of connection requests of the second API group (220) among the number of connection requests by API group, and the CPU information, memory information, disk information, and network information included in the metric information.

[0081] At this time, as shown in FIGS. 5 to 7, the processor (110) calculates the CPU influence (X1) on the metric information using the equations (S1, S2, S3) of a straight line based on the number of connection requests (a1) of the first API group (210), the number of connection requests (a2) of the second API group (220), and the CPU information based on the normal vector (V). " ,X2 " ) can be produced.

[0082] For example, as shown in FIG. 5, when a connection request of the first API group (210) and a connection request of the second API group (220) occur once among the total number of requests, the processor (110) uses the equation (S1) of the straight line based on the normal vector (V) through the adaptive search process (ASP) to determine the CPU impact (X1) of the first API group (210) and the second API group (220) on the metric information. " ,X2 " ) can be produced.

[0083] After this, if the connection request of the first API group (210) and the connection request of the second API group (220) occur twice among the total number of requests, the processor (110) uses the equation (S2) of the straight line based on the normal vector (V) through the adaptive search process (ASP) to determine the CPU impact (X1) of the first API group (210) and the second API group (220) on the metric information. " ,X2 " ) can be produced.

[0084] After this, if the connection request of the first API group (210) and the connection request of the second API group (220) occur three times among the total number of requests, the processor (110) uses the equation (S3) of the straight line based on the normal vector (V) through the adaptive search process (ASP) to determine the CPU impact (X1) of the first API group (210) and the second API group (220) on the metric information. " ,X2 ") can be produced.

[0085] As shown in FIGS. 6 and 7, when the number of connection requests of the first API group (210) and the number of connection requests of the second API group (220) among the total number of requests is set, the processor (110) uses the equation (S) of the straight line based on the normal vector (V) through an adaptive search process to determine the CPU impact (X1) of the first API group (210) and the second API group (220) on the metric information. " ,X2 " ) can be produced.

[0086] Here, the equation of the straight line (S) can be expressed as [Mathematical Formula 1] below.

[0087] [Mathematical Formula 1]

[0088] a1X1+ a2X2= S

[0089] At this time, S may be a change in metric information, a1 may be the number of connection requests of the first API group, a2 may be the number of connection requests of the second API group, X1 may be a CPU impact of the first API group on metric information, and X2 may be a CPU impact of the second API group on metric information.

[0090] At this time, as illustrated in FIG. 6, the processor (110) can find the previous CPU influence (X1', X2') based on the equation of the straight line (a1X1+ a2X2= S), and can obtain the distance (d) from the previous CPU influence (X1', X2') to the equation of the straight line (a1X1+ a2X2= S) based on the normal vector (V).

[0091] Here, the distance (d) can be expressed as [Mathematical Formula 2] below.

[0092] [Equation 2]

[0093]

[0094] At this time, d may be the distance, a1X1+ a2X2 may be the equation of the straight line, S may be the change in metric information, a1 may be the number of connection requests of the first API group, and a2 may be the number of connection requests of the second API group.

[0095] Here, as shown in FIG. 6, the processor (110) draws a line segment of the shortest distance from the previous CPU influence (X1', X2'), and sets the center of the line segment to the current CPU influence (X1) of the first API group (210) and the second API group (220) on the metric information. " ,X2 " ) can be considered. At this time, the processor (110) can be considered as the previous CPU influence (X1', X2') and the current CPU influence (X1 " ,X2 " ) can be performed recursively.

[0096] That is, through [Mathematical Formula 3] to [Mathematical Formula 5] below, a correlation formula between the previous CPU influence and the current CPU influence can be obtained.

[0097] First, the unit vector u of the vector v pointing to the straight line in the previous CPU influence (X1', X2') can be expressed by [Mathematical Formula 3]. At this time, the sign sgn of the vector can be expressed by [Mathematical Formula 4].

[0098] [Equation 3]

[0099]

[0100] [Equation 4]

[0101]

[0102] If we redeploy based on [Equation 3] and [Equation 4], it can be expressed as [Equation 5].

[0103] [Equation 5]

[0104]

[0105] Here, X1 can be the previous influence, and X2 can be the next influence.

[0106] Therefore, based on [Equation 5], it can be generalized into [Equation 6] below.

[0107] [Equation 6]

[0108]

[0109] Here, X n-1 Silver is the previous influence, X n may also have the following effects:

[0110] As shown in FIG. 8, when a connection request of the first API group (210) and a connection request of the second API group (220) occur a preset number of times, the processor (110) uses an equation of a straight line based on a normal vector through an adaptive search process to determine the memory impact (Y1) of the first API group (210) and the second API group (220) on the metric information. " ,Y2 " ) can be produced.

[0111] Here, the equation of the straight line can be expressed as [Mathematical Formula 7] below.

[0112] [Equation 7]

[0113] b1Y1+ b2Y2= S

[0114] At this time, S may be a change in metric information, b1 may be the number of connection requests of the first API group, b2 may be the number of connection requests of the second API group, Y1 may be a memory impact of the first API group on metric information, and Y2 may be a memory impact of the second API group on metric information.

[0115] Here, the processor (110) can find the previous memory influence (Y1', Y2') based on the equation of the straight line (b1Y1+ b2Y2= S), and can obtain the distance from the previous memory influence (Y1', Y2') to the equation of the straight line (b1Y1+ b2Y2= S) based on the normal vector.

[0116] At this time, the processor (110) finds the CPU influence in the same way as the previous memory influence (Y1', Y2') and the current memory influence (Y1 " ,Y2 "" ) can be performed recursively.

[0117] As shown in FIG. 9, when the connection request of the first API group (210) and the connection request of the second API group (220) occur a preset number of times, the processor (110) uses the equation of a straight line based on the normal vector through an adaptive search process to determine the disk impact (Z1) of the first API group (210) and the second API group (220) on the metric information. " ,Z2 " ) can be produced.

[0118] Here, the equation of the straight line can be expressed as [Mathematical Formula 8] below.

[0119] [Equation 8]

[0120] c1Z1+ c2Z2= S

[0121] At this time, S may be a change in metric information, c1 may be the number of connection requests of the first API group, c2 may be the number of connection requests of the second API group, Z1 may be a disk impact of the first API group on metric information, and Z2 may be a disk impact of the second API group on metric information.

[0122] Here, the processor (110) can find the previous disk influence (Z1', Z2') based on the equation of the straight line (c1Z1+ c2Z2= S), and can obtain the distance from the previous disk influence (Z1', Z2') to the equation of the straight line (c1Z1+ c2Z2= S) based on the normal vector.

[0123] At this time, the processor (110) finds the previous disk influence (Z1', Z2') and the current disk influence (Z1) in the same way as the CPU influence. " ,Z2 " ) can be performed recursively.

[0124] As illustrated in FIG. 10, when a connection request of the first API group (210) and a connection request of the second API group (220) occur a preset number of times, the processor (110) uses an equation of a straight line based on a normal vector through an adaptive search process to determine the network impact (Q1) of the first API group (210) and the second API group (220) on the metric information. " ,Q2 " ) can be produced.

[0125] Here, the equation of the straight line can be expressed as [Mathematical Formula 9] below.

[0126] [Equation 9]

[0127] d1Q1+ d2Q2= S

[0128] At this time, S may be a change in metric information, d1 may be the number of connection requests of the first API group, d2 may be the number of connection requests of the second API group, Q1 may be a network impact of the first API group on metric information, and Q2 may be a network impact of the second API group on metric information.

[0129] Here, the processor (110) can find the previous network influence (Q1', Q2') based on the equation of the straight line (d1Q1+ d2Q2= S), and can obtain the distance from the previous network influence (Q1', Q2') to the equation of the straight line (d1Q1+ d2Q2= S) based on the normal vector.

[0130] At this time, the processor (110) finds the previous network influence (Q1', Q2') and the current network influence (Q1) in the same way as the CPU influence. " ,Q2 " ) can be performed recursively.

[0131] Meanwhile, the processor (110) calculates the number of connection requests of the first API group, the number of connection requests of the second API group, and the CPU influence (X1 " ,X2 " ), memory impact (Y1 " ,Y2 " ), disk impact (Z1 " ,Z2 " ) and network influence (Q1 " ,Q2 " ) can also create a quadratic equation, a cubic equation, or a quartic equation based on at least two influences. Since the processor (110) can more precisely analyze the influence on metric information based on the quadratic equation, the cubic equation, or the quartic equation, it can more efficiently control traffic in the traffic generation section and more efficiently allow the entry target to enter.

[0132] In addition, the processor (110) can analyze the influence of two pieces of information among CPU information, memory information, disk information, and network information on metric information using a straight line equation based on a normal vector.

[0133] For example, the processor (110) can analyze the influence of CPU information and memory information on metric information using the equation of a straight line based on a normal vector. As another example, the processor (110) can analyze the influence of CPU information and disk information on metric information using the equation of a straight line based on a normal vector.

[0134] As another example, the processor (110) can analyze the influence of CPU information and network information on metric information using the equation of a straight line based on a normal vector. As another example, the processor (110) can analyze the influence of memory information and disk information on metric information using the equation of a straight line based on a normal vector.

[0135] As another example, the processor (110) can analyze the influence of memory information and network information on metric information using the equation of a straight line based on a normal vector. As another example, the processor (110) can analyze the influence of disk information and network information on metric information using the equation of a straight line based on a normal vector.

[0136] The processor (110) can output change information in metric information based on the number of access requests and influence for each API group (S330). Thereafter, the processor (110) can extract a preset target traffic processing count for each API group based on the change information in the metric information (S340). For example, if the metric in the change information in the metric information is 70, the threshold is 90, and the metric influence is 1.5, the processor (110) can output the target traffic processing count as 13.

[0137] After this, the processor (110) can control the service server (300) to perform traffic control based on the target traffic processing number per API group (S350).

[0138] For example, as illustrated in FIG. 11, when extracting the number of target traffic processed by API group, the processor (110) inputs the change in metric information (S341a), and if the change in metric information is higher than a preset level (example of S341b), the number of connection requests of the first API group and the number of connection requests of the second API group can be further compared (S341c).

[0139] At this time, if the number of connection requests of the first API group is greater than the number of connection requests of the second API group (example of S341d), the processor (110) may further extract the first target traffic processing number of the first API group, which is preset to be smaller than the number of connection requests of the first API group, in order to reduce traffic (S341e).

[0140] Additionally, if the number of connection requests of the second API group is greater than the number of connection requests of the first API group (NO in S341d), the processor (110) may further extract a second target traffic processing number of the second API group, which is preset to be smaller than the number of connection requests of the second API group, in order to reduce traffic (S341f). Here, the first target traffic processing number may be different from the second target traffic processing number.

[0141] As another example, as illustrated in FIG. 12, when extracting the number of target traffic processed by API group, the processor (110) inputs the change in metric information (S342a), and if the change in metric information is higher than a preset level (example of S342b), the average usage time of the first content service linked to the number of connection requests of the first API group and the average usage time of the second content service linked to the number of connection requests of the second API group can be further compared (S342c).

[0142] Here, the first content service and the second content service are different content services, and may be first-come, first-served draws, concert reservations related to course registration, accommodation reservations, ticket reservations, transportation reservations, etc.

[0143] At this time, if the average usage time of the first content service is greater than the average usage time of the second content service (example of S342d), the processor (110) can further extract the third target traffic processing number of the first API group set in advance to reduce traffic (S342e).

[0144] Additionally, if the average usage time of the second content service is greater than the average usage time of the first content service (NO in S342d), the processor (110) may further extract the fourth target traffic processing number of the preset second API group to reduce traffic (S342f). Here, the third target traffic processing number may be different from the fourth target traffic processing number.

[0145] As another example, as illustrated in FIG. 13, when extracting the number of target traffic processed by API group, the processor (110) inputs the change in metric information (S343a), and if the change in metric information is higher than a preset level (example of S343b), the average usage ranking of the first content service linked to the number of connection requests of the first API group and the average usage ranking of the second content service linked to the number of connection requests of the second API group can be further compared (S343c).

[0146] Here, the first content service and the second content service are different content services, and may be first-come, first-served draws, concert reservations related to course registration, accommodation reservations, ticket reservations, transportation reservations, etc.

[0147] At this time, if the average usage ranking of the first content service is faster than the average usage ranking of the second content service (example of S343d), the processor (110) can further extract the fifth target traffic processing number of the first API group set in advance to reduce traffic (S343e).

[0148] Additionally, if the average usage ranking of the second content service is higher than the average usage ranking of the first content service (NO in S343d), the processor (110) may further extract the sixth target traffic processing number of the second API group set to reduce traffic (S343f). Here, the fifth target traffic processing number may be different from the sixth target traffic processing number.

[0149] As another example, as illustrated in FIG. 14, when extracting the number of target traffic processed by API group, the processor (110) inputs the change in metric information (S344a), and if the change in metric information is higher than a preset level (example of S344b), the processing speed of the first content service linked to the number of connection requests of the first API group and the processing speed of the second content service linked to the number of connection requests of the second API group can be further compared (S344c).

[0150] Here, the first content service and the second content service are different content services, and may be first-come, first-served draws, concert reservations related to course registration, accommodation reservations, ticket reservations, transportation reservations, etc.

[0151] At this time, if the processing speed of the first content service is slower than the processing speed of the second content service (example of S344d), the processor (110) can further extract the seventh target traffic processing number of the preset first API group to reduce traffic (S344e).

[0152] Additionally, if the processing speed of the second content service is slower than the processing speed of the first content service (NO in S344d), the processor (110) may further extract the eighth target traffic processing number of the preset second API group to reduce traffic (S344f). Here, the seventh target traffic processing number may be different from the eighth target traffic processing number.

[0153] Meanwhile, although not shown, the traffic control server (100) of the present disclosure may further include an output section and an input section.

[0154] The output unit may display a user interface (UI) for providing information related to operations implemented in the traffic control server (100). The output unit may output any form of information generated or determined by the processor (110) and any form of information received by the communication unit (130).

[0155] The output unit may include at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, and a three-dimensional display (3D display). Some of these display modules may be configured as transparent or light-transmitting so that the outside can be viewed through them. This may be referred to as a transparent display module, and a representative example of the transparent display module is TOLED (Transparent OLED).

[0156] The input unit can receive information input by a user. The input unit can include keys and / or buttons on a user interface, or physical keys and / or buttons, for receiving information input by a user. A computer program for controlling a display according to embodiments of the present disclosure can be executed based on user input through the input unit.

[0157] At least one component may be added or deleted to correspond to the performance of the components illustrated in FIGS. 1 and 2, and FIGS. 4 through 10. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the system.

[0158] Although FIGS. 3 and 11 to 14 describe the sequential execution of multiple steps, this is merely an example of the technical idea of ​​the present embodiment, and a person having ordinary skill in the art to which the present embodiment pertains can modify and apply various modifications and variations by changing the order described in FIGS. 3 and 11 to 14 without departing from the essential characteristics of the present embodiment, or by executing one or more of the multiple steps in parallel. Therefore, FIGS. 3 and 11 to 14 are not limited to a chronological order.

[0159] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0160] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical information storage devices.

[0161] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. A communication unit that communicates with the terminals of users attempting to enter the service server; Memory storing at least one process related to controlling traffic based on impact calculation using metric information; and Includes a processor that performs operations according to the above process, The above processor, Based on the number of connection requests per API group of the user's terminals received from the service server through the communication unit and the metric information, the impact on the metric information is calculated, Based on the number of access requests and the influence for each API group, change information of the metric information is output. Extract the target traffic processing number for each API group set in connection with the change information of the above metric information, Control the service server to control the traffic based on the target traffic processing number for each API group. When extracting the target traffic processing number for each API group, if the change in the metric information is higher than the preset level, the number of connection requests of the first API group and the number of connection requests of the second API group are compared, A traffic control server based on impact calculation using metric information, characterized in that when extracting the target traffic processing number for each API group, if the number of connection requests of the first API group is greater than the number of connection requests of the second API group, the first target traffic processing number of the first API group is extracted to be smaller than the number of connection requests of the first API group in order to reduce the traffic.

2. In paragraph 1, The above processor, A traffic control server based on impact calculation using metric information, characterized in that the impact is calculated based on the number of connection requests of the first API group and the number of connection requests of the second API group among the number of connection requests by API group, and the CPU information, memory information, disk information, and network information included in the metric information.

3. In paragraph 2, The above processor, A traffic control server based on influence calculation using metric information, characterized in that the influence is calculated using the equation of a straight line based on a normal vector, based on the number of connection requests of the first API group, the number of connection requests of the second API group, and at least one of the CPU information, memory information, disk information, and network information.

4. In paragraph 2, The above processor, A traffic control server based on impact calculation using metric information, characterized in that when the number of connection requests of the second API group is greater than the number of connection requests of the first API group, a second target traffic processing number of the second API group, which is preset to be smaller than the number of connection requests of the second API group, is further extracted to reduce the traffic.

5. In paragraph 2, The above processor, When extracting the target traffic processing number for each API group above, If the change in the above metric information is higher than the preset level, the average usage time of the first content service linked to the number of access requests of the first API group and the average usage time of the second content service linked to the number of access requests of the second API group are further compared, If the average usage time of the first content service is greater than the average usage time of the second content service, the third target traffic processing number of the first API group set in advance is further extracted to reduce the traffic. A traffic control server based on impact calculation using metric information, characterized in that when the average usage time of the second content service is greater than the average usage time of the first content service, a fourth target traffic processing number of the second API group set in advance is further extracted to reduce the traffic.

6. In paragraph 2, The above processor, When extracting the target traffic processing number for each API group above, If the change in the above metric information is higher than the preset level, the average usage ranking of the first content service linked to the number of access requests of the first API group and the average usage ranking of the second content service linked to the number of access requests of the second API group are further compared, If the average usage ranking of the first content service is faster than the average usage ranking of the second content service, the fifth target traffic processing number of the first API group set in advance is further extracted to reduce the traffic. A traffic control server based on impact calculation using metric information, characterized in that when the average usage ranking of the second content service is faster than the average usage ranking of the first content service, the sixth target traffic processing number of the second API group set in advance is further extracted to reduce the traffic.

7. In paragraph 2, The above processor, When extracting the target traffic processing number for each API group above, If the change in the above metric information is higher than the preset level, the processing speed of the first content service linked to the number of connection requests of the first API group and the processing speed of the second content service linked to the number of connection requests of the second API group are further compared, If the processing speed of the first content service is slower than the processing speed of the second content service, the seventh target traffic processing number of the first API group set in advance is further extracted to reduce the traffic. A traffic control server based on impact calculation using metric information, characterized in that when the processing speed of the second content service is slower than the processing speed of the first content service, the eighth target traffic processing number of the second API group set in advance is further extracted to reduce the traffic.

8. Service server providing content services; Terminals of users attempting to enter the above service server; and Includes a traffic control server that performs communication with the above service server and the user's terminals, The above traffic control server, Based on the number of connection requests and metric information for each API group of the user's terminals received from the service server, the impact on the metric information is calculated, Based on the number of access requests and the influence for each API group, change information of the metric information is output. Extract the target traffic processing number for each API group set in connection with the change information of the above metric information, Control the service server to control the traffic based on the target traffic processing number for each API group. When extracting the target traffic processing number for each API group, if the change in the metric information is higher than the preset level, the number of connection requests of the first API group and the number of connection requests of the second API group are compared, A traffic control system based on impact calculation using metric information, characterized in that when extracting the target traffic processing number for each API group, if the number of connection requests of the first API group is greater than the number of connection requests of the second API group, the first target traffic processing number of the first API group is extracted to be smaller than the number of connection requests of the first API group in order to reduce the traffic.

9. In paragraph 8, The above traffic control server, A traffic control system based on impact calculation using metric information, characterized in that the impact is calculated based on the number of connection requests of the first API group and the number of connection requests of the second API group among the number of connection requests by API group, and CPU information, memory information, disk information, and network information included in the metric information.

10. In paragraph 9, The above traffic control server, A traffic control system based on influence calculation using metric information, characterized in that the influence is calculated using the equation of a straight line based on a normal vector, based on the number of connection requests of the first API group, the number of connection requests of the second API group, and at least one of the CPU information, memory information, disk information, and network information.

11. In paragraph 9, The above traffic control server, A traffic control system based on impact calculation using metric information, characterized in that when the number of connection requests of the second API group is greater than the number of connection requests of the first API group, a second target traffic processing number of the second API group, which is preset to be smaller than the number of connection requests of the second API group, is further extracted to reduce the traffic.

12. In paragraph 9, The above traffic control server, When extracting the target traffic processing number for each API group above, If the change in the above metric information is higher than the preset level, the average usage time of the first content service linked to the number of access requests of the first API group and the average usage time of the second content service linked to the number of access requests of the second API group are further compared, If the average usage time of the first content service is greater than the average usage time of the second content service, the third target traffic processing number of the first API group set in advance is further extracted to reduce the traffic. A traffic control system based on impact calculation using metric information, characterized in that when the average usage time of the second content service is greater than the average usage time of the first content service, a fourth target traffic processing number of the second API group set in advance is further extracted to reduce the traffic.

13. In paragraph 9, The above traffic control server, When extracting the target traffic processing number for each API group above, If the change in the above metric information is higher than the preset level, the average usage ranking of the first content service linked to the number of access requests of the first API group and the average usage ranking of the second content service linked to the number of access requests of the second API group are further compared, If the average usage ranking of the first content service is faster than the average usage ranking of the second content service, the fifth target traffic processing number of the first API group set in advance is further extracted to reduce the traffic. A traffic control system based on impact calculation using metric information, characterized in that when the average usage ranking of the second content service is faster than the average usage ranking of the first content service, a sixth target traffic processing number of the second API group set in advance to reduce the traffic is further extracted.

14. In paragraph 9, The above traffic control server, When extracting the target traffic processing number for each API group above, If the change in the above metric information is higher than the preset level, the processing speed of the first content service linked to the number of connection requests of the first API group and the processing speed of the second content service linked to the number of connection requests of the second API group are further compared, If the processing speed of the first content service is slower than the processing speed of the second content service, the seventh target traffic processing number of the first API group set in advance is further extracted to reduce the traffic. A traffic control system based on impact calculation using metric information, characterized in that when the processing speed of the second content service is slower than the processing speed of the first content service, the eighth target traffic processing number of the second API group set in advance is further extracted to reduce the traffic.

Images