WO2022013907A1 - Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program - Google Patents

Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program Download PDF

Info

Publication number
WO2022013907A1
WO2022013907A1 PCT/JP2020/027200 JP2020027200W WO2022013907A1 WO 2022013907 A1 WO2022013907 A1 WO 2022013907A1 JP 2020027200 W JP2020027200 W JP 2020027200W WO 2022013907 A1 WO2022013907 A1 WO 2022013907A1
Authority
WO
WIPO (PCT)
Prior art keywords
delay time
computing resource
communication
route
computing
Prior art date
Application number
PCT/JP2020/027200
Other languages
French (fr)
Japanese (ja)
Inventor
健太 篠原
Original Assignee
日本電信電話株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電信電話株式会社 filed Critical 日本電信電話株式会社
Priority to JP2022535987A priority Critical patent/JP7435783B2/en
Priority to PCT/JP2020/027200 priority patent/WO2022013907A1/en
Publication of WO2022013907A1 publication Critical patent/WO2022013907A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H04L45/121—Shortest path evaluation by minimising delays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/28—Flow control; Congestion control in relation to timing considerations
    • H04L47/283—Flow control; Congestion control in relation to timing considerations in response to processing delays, e.g. caused by jitter or round trip time [RTT]

Definitions

  • the present invention relates to a relay device, a distribution device, a route switching method of the relay device, a route switching method of the distribution device, and a program.
  • MEC Multi-Access Edge Computing
  • the MEC computing resource is deployed in the Data Network connected to the user plane function (UPF: User Plane Function) (see, for example, Non-Patent Document 2).
  • UPF User Plane Function
  • the MEC is deployed near the UPF, and together with the UPF, various deployment patterns are possible.
  • Multi-access Edge Computing [online], ETSI, [Search on July 2, 2nd year of Reiwa], Internet ⁇ https://www.etsi.org/technologies/multi-access-edge-computing /> > Sami Kekki, 15 others, “MEC in 5G networks”, [online], June 2018, ETSI, [Search on July 2, 2nd year of Reiwa], Internet ⁇ https://www.etsi.org/images /files/ETSIWhitePapers/etsi_wp28_mec_in_5G_FINAL.pdf >
  • the communication terminal (UE: User Equipment) communicates with the preset UPF, and the computing resource (MEC) deployed in the vicinity of the UPF executes calculation processing and the like.
  • the usage rate of the computing resource is high, the processing in the computing resource is waiting in order and delay occurs, or some kind of communication failure occurs and the computing resource becomes unusable.
  • the UE since the UE is connected to the computing resource deployed in the vicinity of the UPF, the low latency that the MEC is trying to realize is lost.
  • the present invention has been made in view of such a point, and the present invention has a high utilization rate of computing resources, a situation in which processing by computing resources is waiting in order and a delay occurs, or some kind of failure in communication.
  • To provide a low-latency service by dynamically switching the route so that the communication terminal is connected to the computing resource with the least amount of delay even if the computing resource becomes unavailable. Is the subject.
  • the relay device In response to a connection request from a communication terminal to a computing resource, the communication delay time from the communication terminal to each computing resource that can be connected to the communication terminal is calculated, and the communication delay time is calculated.
  • the processing delay time in each of the computing resources is calculated, and based on the processing delay time in each of the computing resources and the communication delay time from the communication terminal to each of the computing resources, each of the computing from the communication terminal.
  • a total delay time calculation unit that calculates the total delay time for each route to the ing resource,
  • a route switching unit that switches the route so that the communication terminal is connected to the computing resource having the shortest total delay time among the calculated total delay times for each route to the computing resource. , It is characterized by having.
  • the present invention it is possible to dynamically switch a route so as to connect a communication terminal to a computing resource having the least amount of delay, and to provide a service with low delay.
  • MEC Multi-Access Edge Computing
  • FIG. 7 is a block diagram showing a schematic configuration (network structure) of a MEC in a 5G mobile network, which is a conventional technique.
  • UE User Equipment
  • RAN Radio Access Network
  • AMF Access and Mobility Management Function
  • NSSF Network Slice Selection Function
  • NRF Network Resource Function
  • UDM Unified Data Management
  • PCF Policy Control Function
  • NEF Network Exposure Function
  • AUSF Authentication Server Function
  • SMF Session Management Function
  • PCF Policy Control Function
  • UPF User Plane Function
  • MEC Multi-Access Edge Computing
  • UE201 indicates a communication terminal (wireless terminal).
  • RAN202 shows a network composed of a radio base station, a radio line control device, and the like.
  • AMF 203 shows the function of managing access and mobility.
  • NSSF204 shows a function of selecting a network slice instance suitable for the user.
  • NRF205 shows network functions and the ability to register the services they generate.
  • UDM206 describes the functionality responsible for many services related to users and subscriptions.
  • PCF207 demonstrates the ability to control policies and rules for 5G systems.
  • the NEF 208 acts as a centralized point for publishing services and is responsible for approving all connection requests originating from outside the system.
  • AUSF209 shows the ability to handle procedures related to authentication.
  • the SMF210 shows a function of managing sessions.
  • the PCF211 like the PCF207, exhibits the ability to control 5G policies and rules.
  • UPF212 shows a function of forwarding a packet of user data.
  • the MECSystem300 has a MECOrchester311, which constitutes a system-level functional entity. Further, the MECSystem 300 provides a service as an application function of a 5G network by the MEC Platform 322 managed by the MEC Platform Manager 323 at the distributed host level.
  • Data Network 321 of MECSystem300 is a general term for networks to which servers that provide services such as the Internet are connected.
  • the Data Network 321 is supported by the 5G core network (CoreNetwork) to connect to the LA / DN (Local Area / Data Network) in a specific area where the application (APP) is deployed.
  • CoreNetwork 5G core network
  • LA / DN Local Area / Data Network
  • the location where the UPF212 and MEC computing resources are deployed can be determined relatively freely.
  • the UPF212 to which the computing resources of the MEC are connected may be deployed near the base station or may be deployed in the core network.
  • FIG. 8 is an explanatory diagram showing four examples EX1 to EX4 of actual physical deployment of MEC (computing resource). The same components are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
  • Example EX1 in FIG. 8 shows an example in which MEC421 and a local UPF411 are deployed at a base station.
  • the MEC421 is connected to the UPF411 deployed together with the base station 401.
  • the MEC422 is connected to the UPF412 deployed together with the base station 402.
  • the MEC 421 and 422 are connected to the CN (Core Network) 441 via the router 431.
  • Example EX2 in FIG. 8 shows an example in which MEC421 is deployed at a transmission node together with a local UPF411.
  • the base station 401 is connected to UPF411, and the base station 403 is connected to MEC421.
  • UPF411 and MEC421 are connected to CN441 via router 431.
  • Example EX3 in FIG. 8 shows an example in which MEC421 and the local UPF411 are integrated and deployed in the network.
  • the MEC421 and the local UPF411 are integrally connected to the CN441 via the router 431.
  • the base stations 401, 402, and 403 are connected to the router 431.
  • Example EX4 in FIG. 8 shows an example in which MEC421 and 422 are deployed in the core network of the same data center.
  • the MEC421 is connected to the UPF411 in the CN441
  • the MEC422 is connected to the UPF412 in the CN441.
  • the UPF411,412 connected to the MEC421,422 may be deployed near the base station, or may be deployed in the core network.
  • the communication terminal in Tokyo is usually set to be connected to the MEC in Tokyo.
  • the communication terminal in the communication terminal in Tokyo may be suppressed by connecting to the MEC of the base in Osaka.
  • the MECs of Tokyo and Osaka are connected by a public cloud or a dedicated line, and the processing on the communication terminal can be processed by either the MECs of Tokyo and Osaka.
  • the UE (not shown) is connected to the MEC421 via the base station 401 and the UPF411.
  • MEC421 is a server installed at a base in Tokyo
  • MEC422 is a server installed at a base in Osaka.
  • the MEC421 installed at the base in Tokyo has a high utilization rate of computing resources and is in a situation where there is a delay due to waiting for processing.
  • the MEC422 installed at the base in Osaka has a low computing resource usage rate and a low communication delay.
  • the UE (not shown) connected to the base station 401 is connected to the MEC421 installed at the base in Tokyo, but if the communication delay or the processing delay is large in the MEC421, the router 431 and the UPF412 are used. Therefore, it is desirable to connect to the MEC422 installed at the base in Osaka to avoid communication delays and processing delays.
  • the relay device includes a total delay time calculation unit and a route switching unit, and has a delay time for each route to each computing resource (MEC).
  • the UE is characterized by switching the route connected to the computing resource (MEC) so that the UE is connected to the computing resource (MEC) having the shortest delay time.
  • the distribution device includes a delay time calculation unit and a route switching unit, and delays from the own device to the first computing resource (MEC).
  • the time is compared with the delay time from the own device to the second computing resource (MEC) so that the UE is connected to the computing resource (MEC) having the shorter delay time from the own device to the first or second computing resource (MEC). It is characterized by switching the route to the second computing resource (MEC).
  • the relay device according to the first embodiment and the distribution device according to the second embodiment dynamically switch the route so as to connect the UE to the computing resource (MEC) having the least delay amount. , Can provide low latency service.
  • the relay device calculates the communication delay time from the communication terminal to each computing resource that can connect to the communication terminal in response to the connection request from the communication terminal to the computing resource.
  • the processing delay time for each computing resource is calculated, and each computing resource from the communication terminal is based on the processing delay time for each computing resource and the communication delay time from the communication terminal to each computing resource.
  • the communication terminal connects to the computing resource with the shortest total delay time among the total delay time calculation unit that calculates the total delay time for each route to and the calculated total delay time for each route to each computing resource. It is provided with a route switching unit for switching routes so as to be performed.
  • FIG. 1 is a diagram illustrating an example of a communication path of the network system 500 in which the relay device 40 according to the first embodiment is arranged.
  • the network system 500 includes a UE (User Equipment: communication terminal) 10, a base station 20, a relay device 30, a relay device 40, an UPF (User Plane Function) 50, and a MEC (Multi-). Access Edge Computing) 60, relay device 70, UPF80, and MEC90 are provided.
  • the network system 500 includes a communication path from the UE 10 to the MEC 60 (first communication path) and a communication path from the UE 10 to the MEC 90 (second communication path).
  • the first communication path is composed of the communication path of the UE 10, the base station 20, the relay device 30, the relay device 40, the UPF50, and the MEC60.
  • the second communication path is composed of the communication path of the UE 10, the base station 20, the relay device 30, the relay device 40, the relay device 70, the UPF80, and the MEC90. First, the first communication path will be described.
  • UE 10 indicates a communication terminal (wireless terminal) used by the user.
  • the base station 20 is a device that connects and terminates a wireless section with the UE 10.
  • the communication delay from the UE 10 to the base station 20 is defined as ⁇ a.
  • the relay devices 30 and 40 are devices that relay the network between the base station 20 and the UPF 50.
  • the communication delay from the base station 20 to the relay device 30 is defined as ⁇ b. Further, the communication delay from the relay device 30 to the relay device 40 is defined as ⁇ c.
  • the relay devices 30 and 40 are configured to include a total delay time calculation unit 41 and a route switching unit 42.
  • the relay device 40 will be used as an example.
  • the total delay time calculation unit 41 calculates the communication delay time from the UE 10 to each MEC60, 90 that can connect to the UE 10 in response to the connection request from the UE 10 to the MEC60, and also calculates the processing delay time in each MEC60, 90. It also has a function to calculate the total delay time for each route from UE 10 to MEC 60, 90 based on the processing delay time in each MEC 60, 90 and the communication delay time from UE 10 to each MEC 60, 90. There is.
  • the route switching unit 42 connects the UE 10 to the MEC 60, 90 so that the UE 10 is connected to the MEC 60, 90 having the shortest total delay time among the calculated total delay times for each MEC 60, 90. It has a function to switch the route.
  • the UPF 50 has a function of transferring a packet of user data from the base station 20 to the MEC 60.
  • the UPF 50 functions as, for example, a router responsible for forwarding data packets.
  • the communication delay from the relay device 40 to the UPF 50 is defined as ⁇ d.
  • MEC60 is a technology that realizes low latency, and is a server (computing resource) deployed in the vicinity of UPF50.
  • the communication delay from UPF50 to MEC60 is defined as ⁇ e.
  • the processing delay (processing delay time) in MEC60 is defined as ⁇ .
  • the second communication path is composed of the UE 10, the base station 20, the relay device 30, the relay device 40, the relay device 70, the UPF80, and the MEC90.
  • the same components as those of the first communication path are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
  • the second communication path is configured to include the same communication path as the first communication path from the UE 10 to the relay device 40.
  • the relay device 70 is a relay device having the same configuration as the relay devices 30 and 40.
  • the communication delay from the relay device 40 to the relay device 70 is defined as ⁇ f.
  • the UPF80 has a function of transferring a packet of user data from the base station 20 to the MEC90.
  • the UPF80 is a device having the same configuration as the UPF50.
  • the communication delay from the relay device 70 to the UPF80 is defined as ⁇ g.
  • the MEC90 has the same configuration as the MEC60, and is a server (computing resource) deployed in the vicinity of the UPF80.
  • the communication delay from UPF80 to MEC90 is defined as ⁇ h.
  • the processing delay (processing delay time) in MEC90 is defined as ⁇ .
  • the above-mentioned communication delays ⁇ a to ⁇ h are calculated based on parameters such as the path length, transmission capacity, and packet length of each communication section.
  • ⁇ and ⁇ indicating the above-mentioned processing delay indicate the delay amount in each MEC 60, 90, and are generated, for example, the number of CPU (Central Processing Unit) processing wait queues of each server or when the CPU is switched. It is calculated based on the number of context switches, the number of packet reception queues, the delay amount measurement result of the delay measurement packet, and the like.
  • the communication delay and the processing delay (processing delay time) may take into account the tendency of the latest delay change (for example, the delay time tends to increase).
  • the MEC60, 90 related to the UE 10 is set to which UPF 50, 80 by the packet transmitted from the UE 10 or the preset setting based on the contract information of the user. It shall be contained or preset.
  • the relay devices 30, 40, 70, the UPF 50, 80, and the MEC 60, 90 are always communicating with each other, and the relay devices 30, 40, 70 have communication delays ⁇ a to ⁇ h and processing delays (processing delays). All values of ⁇ and ⁇ of (time) are stored. It is assumed that the UE 10 is set to be connected to the MEC 60 by a prior setting.
  • FIG. 2 is a flowchart showing the flow of the route switching process executed by the relay device 40 according to the first embodiment.
  • the relay device 40 calculates the total delay time DT1 (delay time of the first communication path) from the UE 10 to the MEC 60 (step S001).
  • the total delay time calculation unit 41 of the relay device 40 has ⁇ a of the communication delay of the base station 20 connected to the UE 10, ⁇ b of the communication delay of the relay device 30 connected to the base station 20, and the relay device 30.
  • the total communication delay time (sum of ⁇ a to ⁇ e) of the communication delay ⁇ c of the relay device 40 connected to the relay device 40, the communication delay ⁇ d of the UPF 50 connected to the relay device 40, and the communication delay ⁇ e of the MEC 60 connected to the UPF 50. ) Is calculated.
  • the total delay time calculation unit 41 calculates the processing delay time ⁇ in the MEC60, and based on the processing delay time ⁇ in the MEC60 and the total communication delay time (sum of ⁇ a to ⁇ e) up to the MEC60, the UE 10
  • the total delay time DT1 (sum of ⁇ a to ⁇ e + ⁇ ) from to MEC60 is calculated.
  • the relay device 40 calculates the total delay time DT2 (delay time of the second communication path) from the UE 10 to the MEC 90 (step S003).
  • the total delay time calculation unit 41 of the relay device 40 has ⁇ a of the communication delay of the base station 20 connected to the UE 10, ⁇ b of the communication delay of the relay device 30 connected to the base station 20, and the relay device 30.
  • the total communication delay time (sum of ⁇ a to ⁇ h) of ⁇ h of the communication delay is calculated.
  • the total delay time calculation unit 41 calculates the processing delay time ⁇ in the MEC 90, and based on the processing delay time ⁇ in the MEC 90 and the total communication delay time (the sum of ⁇ a to ⁇ h) up to the MEC 90, the UE 10
  • the total delay time DT2 (sum of ⁇ a to ⁇ h + ⁇ ) from to MEC90 is calculated.
  • the relay device 40 determines whether or not the total delay time DT1 of the first communication path is equal to or less than the total delay time DT2 of the second communication path (step S005), and the total delay time DT1 is the total delay time DT2. In the following case (Yes in step S005), it is determined that the processing in MEC60 is appropriate, the UE 10 is connected to MEC60 (step S007), and the route switching processing is terminated.
  • the total delay time DT1 of the first communication path is larger than the total delay time DT2 of the second communication path (No in step S005)
  • the total delay time is processed by MEC90 rather than by MEC60.
  • the relay device 40 switches the route so that the UE 10 is connected to the MEC 90 (step S009), and ends the process.
  • the route switching unit 42 of the relay device 40 connects the UE 10 to the MEC 60, 90 having the shortest total delay time among the calculated total delay times for each route of the MEC 60, 90. Switches the route connected to MEC60,90.
  • the relay device 40 is low by dynamically switching the path of the MEC so as to connect to the MEC having the smallest delay amount (for example, total delay time). It is possible to provide delayed service.
  • the total delay time calculation unit 41 of the relay device 40 calculates the total delay time, and the route switching unit 42 switches the route from the UE 10 to the MEC 60, 90.
  • the relay device 70 calculates the total delay time instead of the total delay time calculation unit 41 of the relay device 40, and the route switching unit 42 of the relay device 40 calculates the total delay time based on the total delay time.
  • MEC60, 90 may be dynamically switched.
  • the relay device 70 when the route switching unit 42 of the relay device 40 switches the route of the UE 10 from the first communication path to the second communication path, the relay device 70 further calculates the total delay time. Then, the route switching unit 42 of the relay device 40 may switch the route from the UE 10 to the MECs 60 and 90 based on the total delay time.
  • the relay device 30 may calculate the total delay time instead of the total delay time calculation unit 41 of the relay device 40, and the route switching unit 42 of the relay device 40 may calculate the total delay time based on the total delay time.
  • the route from UE 10 to MEC 60, 90 may be switched.
  • the distribution device communicates from the distribution device, which is its own device, to the first computing resource in response to a connection request from the communication terminal to the first computing resource. Based on the delay and the processing delay in the first computing resource, the delay time from the own device to the first computing resource is calculated, and the second device different from the first computing resource is calculated.
  • the delay time calculation unit that calculates the communication delay to the computing resource of the above and the processing delay in the second computing resource, and calculates the delay time from the own device to the second computing resource, and the own device.
  • the delay time to the first computing resource is compared with the delay time from the own device to the second computing resource, and the own device is connected so that the communication terminal is connected to the computing resource having the shorter delay time. It is provided with a route switching unit for switching a route from the first to the first or second computing resource.
  • FIG. 3 is a diagram illustrating an example of a communication path of the network system 501 in which the distribution device 100 according to the second embodiment is arranged.
  • the network system 501 is configured to include a distribution device 100 between the UPF 50 and the MEC 60.
  • the network system 501 is configured to include a distribution device 110 between the UPF 80 and the MEC 90.
  • the network system 501 includes a UE 10, a base station 20, a relay device 30, a relay device 40, an UPF 50, a distribution device 100, a MEC 60, a relay device 70, an UPF 80, a distribution device 110, and a MEC 90. It is composed of.
  • the network system 501 includes a communication path from the distribution device 100 to the MEC60 (third communication path) and a communication path from the distribution device 100 to the MEC90 (fourth communication path). ..
  • the same components as those in the first embodiment are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
  • the distribution devices 100 and 110 are arranged between the UPF 50 and 80 and the MEC 60 and 90, but the present invention is not limited to this.
  • the functions of the distribution devices 100 and 110 according to the second embodiment may be provided in the UPFs 50 and 80, and the UPFs 50 and 80 may perform the same processing as the distribution devices 100 and 110, or the distribution devices may be executed.
  • the functions of 100 and 110 may be provided in the MECs 60 and 90, and the MECs 60 and 90 may execute the same processing as the distribution devices 100 and 110.
  • the third communication path is composed of the distribution device 100 and the MEC60.
  • the fourth communication path is composed of a distribution device 100, an UPF 50, a relay device 40, a relay device 70, an UPF 80, a distribution device 110, and a MEC 90.
  • the communication delay from the UPF 50 to the distribution device 100 is ⁇ e
  • the communication delay from the distribution device 100 to the MEC 60 is ⁇ i
  • the communication delay from the UPF 80 to the distribution device 110 is defined as ⁇ h
  • the communication delay from the distribution device 110 to the MEC 90 is defined as ⁇ j.
  • the distribution devices 100 and 110 according to the second embodiment are different from the first embodiment only in the distribution devices 100 and 110, the relay devices 30, 40, 70, UPF 50, 80, and MEC 60, 90. And stores ⁇ a to ⁇ j indicating a communication delay and values of ⁇ and ⁇ indicating a processing delay (processing delay time). Therefore, the relay devices 30, 40, 70, UPF 50, 80, and MEC 60, 90 do not need to communicate with each other.
  • the distribution devices 100 and 110 are configured to include a delay time calculation unit 101 and a route switching unit 102.
  • the sorting device 100 will be used as an example.
  • the delay time calculation unit 101 determines the delay time from the distribution device 100 to the MEC60 based on the communication delay from the distribution device 100 to the MEC60 and the processing delay in the MEC60 in response to the connection request from the UE 10 to the MEC60. In addition to the calculation, it has a function of calculating the communication delay from the distribution device 100 to the MEC90 different from the MEC60 and the processing delay in the MEC90, and calculating the delay time from the distribution device 100 to the MEC90.
  • the route switching unit 102 compares the delay time from the distribution device 100 to the MEC60 with the delay time from the distribution device 100 to the MEC90 so that the UE 10 is connected to the computing resource having the short delay time. It has a function of switching the route from the distribution device 100 to the MECs 60 and 90.
  • the distribution device 100 when the connection request is transmitted from the UE 10 preset to be connected to the MEC 60, the distribution device 100 has the preset contents. Based on this, the connection request is received via the relay device 30, the relay device 40, and the UPF 50.
  • FIG. 4 is a flowchart showing the flow of the route switching process executed by the distribution device 100 according to the second embodiment.
  • the distribution device 100 calculates the delay time DT3 (delay time of the third communication path) from the distribution device 100 to the MEC 60 (step S101).
  • the delay time calculation unit 101 of the distribution device 100 has a communication delay ⁇ i of the MEC60 (first computing resource) connected to the distribution device 100 and the MEC60 (first computing resource). ), The delay time DT3 ( ⁇ i + ⁇ ) from the distribution device 100 to the MEC60 (first computing resource) is calculated based on the processing delay ⁇ .
  • the distribution device 100 calculates the delay time DT4 (delay time of the fourth communication path) from the distribution device 100 to the MEC90 (step S103).
  • the delay time calculation unit 101 of the distribution device 100 sets the communication delay ⁇ e of the UPF 50 connected to the distribution device 100, the communication delay ⁇ d of the relay device 40 connected to the UPF 50, and the relay device 40.
  • ⁇ f of communication delay of connected relay device 70, ⁇ g of communication delay of UPF80 connected to relay device 70, ⁇ h of communication delay of distribution device 110 connected to UPF80, MEC90 connected to distribution device 110 Delay from distribution device 100 to MEC90 (second computing resource) based on communication delay ⁇ j of (second computing resource) and processing delay ⁇ in MEC90 (second computing resource).
  • the time DT4 ( ⁇ e + ⁇ d + ⁇ f + ⁇ g + ⁇ h + ⁇ j + ⁇ ) is calculated.
  • the distribution device 100 determines whether or not the delay time DT3 of the third communication path is the delay time DT4 or less of the fourth communication path (step S105), and when the delay time DT3 is the delay time DT4 or less. (Yes in step S105), it is determined that the processing in MEC60 is appropriate, the UE 10 is connected to MEC60 (step S107), and the route switching processing is terminated.
  • the delay time DT3 of the third communication path is larger than the delay time DT4 of the fourth communication path (No in step S105)
  • the delay time is shorter when processed by MEC90 than when processed by MEC60.
  • the distribution device 100 switches the route so that the UE 10 is connected to the MEC 90 (step S109), and ends the process.
  • the route switching unit 102 of the distribution device 100 compares the delay time DT3 from the distribution device 100 to the MEC60 with the delay time DT4 from the distribution device 100 to the MEC90, and the MEC60 has a shorter delay time.
  • the route from the distribution device 100 to the MECs 60 and 90 is switched so that the UE 10 is connected to the and 90.
  • the distribution device 100 sets in the connection request message that the connection destination is MEC90.
  • the distribution device 100 is connected to the MEC60, 90 having the smallest delay amount (for example, delay time). By dynamically switching the routes of, 90, it is possible to provide a low-latency service.
  • ⁇ Third embodiment> instead of the relay device 40 according to the first embodiment or the distribution device 100 according to the second embodiment, an aggregation device is separately arranged, and a calculation unit and a route are provided in the aggregation device. A decision unit is provided.
  • the aggregation device can determine the route of the connection destination MEC60, 90 to which the UE 10 is connected, the UE 10 or the base station 20 first makes an inquiry to the aggregation device to connect to the connection destination.
  • the MEC60,90 and the route connected to the MEC60,90 can be acquired.
  • FIG. 5 is a diagram illustrating an example of a communication path of the network system 502 in which the aggregation device 120 according to the third embodiment is arranged.
  • FIG. 5 shows the configuration of the network system 502 in which the aggregation device 120 is further arranged in the network system 500 in which the relay device 40 according to the first embodiment is arranged.
  • the aggregation device 120 includes a calculation unit 121 and a routing unit 122.
  • the calculation unit 121 has a function of the total delay time calculation unit 41 of the relay device 40 or the delay time calculation unit 101 of the distribution device 100. That is, the calculation unit 121 has a function of calculating the total delay time for each route from the UE 10 to each MEC60, 90 in response to a connection request from the UE 10 to the MEC60, or has a function of calculating the total delay time from the aggregation device 120, which is its own device, to each MEC60. It has a function to calculate the delay time up to 90.
  • the route determination unit 122 has the most total delay time among the calculated total delay times for each route up to MEC60, 90. It has a function of determining a route so that the UE 10 is connected to the short MECs 60 and 90.
  • the route determination unit 122 compares the delay times from the aggregation device 120, which is its own device, to the MECs 60 and 90, respectively. It has a function of determining a route so that the UE 10 is connected to the MECs 60 and 90 having a short delay time.
  • the aggregation device 120 receives an inquiry request from the UE 10 or the base station 20.
  • the aggregation device 120 calculates the total delay time for each route from the UE 10 to each MEC60, 90 in the calculation unit 121, or calculates the delay time from the aggregation device 120, which is its own device, to each MEC60, 90. ..
  • the route determination unit 122 determines the route to which the UE 10 is connected to the MECs 60 and 90 having the shortest total delay time, or determines the route to which the UE 10 is connected to the MECs 60 and 90 having the shortest delay time as a result of comparing the delay times. Then, the route is answered (response) to the UE 10 or the base station 20.
  • the aggregation device 120 can respond (respond) to the route of the connection destination MEC60, 90 capable of providing the UE 10 or the aggregation device 120 with a low delay service, so that the UE 10 or the base station 20 can respond.
  • the network system 502 it is possible to acquire a route for connecting the UE 10 to the MECs 60 and 90 having a small delay amount.
  • the relay device 40 can switch the connection destination of the UE 10 by acquiring a route for connecting the UE 10 to the MECs 60 and 90 having a small delay amount.
  • the relay devices 30, 40, 70 according to the first embodiment, the distribution devices 100, 110 according to the second embodiment, and the aggregation device 120 according to the third embodiment are, for example, as shown in FIG. It is realized by a computer 900.
  • FIG. 6 shows the functions of the relay devices 30, 40, 70 according to the first embodiment, the functions of the distribution devices 100, 110 according to the second embodiment, and the aggregation device 120 according to the third embodiment. It is a hardware block diagram which shows an example of the computer 900 which realizes a function.
  • the computer 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, an HDD (Hard Disk Drive) 904, an input / output I / F (Interface) 905, and a communication I / F 906. , And media I / F907.
  • CPU Central Processing Unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • HDD Hard Disk Drive
  • the CPU 901 operates based on the program stored in the ROM 902 or the HDD 904, and functions as the total delay time calculation unit 41 and the route switching unit 42 of the relay device 40 shown in FIG. Further, the CPU 901 operates based on the program stored in the ROM 902 or the HDD 904, and functions as the delay time calculation unit 101 and the route switching unit 102 of the distribution device 100 shown in FIG. Further, the CPU 901 operates based on the program stored in the ROM 902 or the HDD 904, and functions as the calculation unit 121 and the routing unit 122 of the aggregation device 120 shown in FIG.
  • the ROM 902 stores a boot program executed by the CPU 901 when the computer 900 is started, a program related to the hardware of the computer 900, and the like.
  • the CPU 901 controls an input device 910 such as a mouse and a keyboard and an output device 911 such as a display via the input / output I / F 905.
  • the CPU 901 acquires data from the input device 910 and outputs the generated data to the output device 911 via the input / output I / F 905.
  • a GPU or the like may be used together with the CPU 901 as the processor.
  • the HDD 904 stores a program executed by the CPU 901, data used by the program, and the like.
  • the communication I / F906 receives data from another device via a communication network (for example, NW (Network) 920) and outputs the data to the CPU 901, and the communication I / F 906 transfers the data generated by the CPU 901 to another device via the communication network. Send to the device.
  • NW Network
  • the media I / F907 reads the program or data stored in the recording medium 912 and outputs the program or data to the CPU 901 via the RAM 903.
  • the CPU 901 loads the program related to the target processing from the recording medium 912 onto the RAM 903 via the media I / F 907, and executes the loaded program.
  • the recording medium 912 is an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto Optical disk), a magnetic recording medium, a conductor memory tape medium, a semiconductor memory, or the like. Is.
  • the CPU 901 of the computer 900 executes the program loaded on the RAM 903 to function the relay device 40 (total delay time calculation unit). 41, the route switching unit 42) is realized.
  • the CPU 901 of the computer 900 executes the program loaded on the RAM 903 to execute the function of the distribution device 100 (delay time calculation).
  • Unit 101, route switching unit 102) is realized.
  • the CPU 901 of the computer 900 executes the program loaded on the RAM 903 to execute the function of the aggregation device 120 (calculation unit 121, route).
  • the determination unit 122) is realized.
  • the data in the RAM 903 is stored in the HDD 904.
  • the CPU 901 reads the program related to the target processing from the recording medium 912 and executes it.
  • the CPU 901 may read a program related to the target processing from another device via the communication network (NW920).
  • the relay device 40 calculates the communication delay time from the UE 10 to each MEC60, 90 that can connect to the UE 10 in response to the connection request from the UE 10 to the MEC60, and also calculates the processing delay time in each MEC60, 90. Total delay time calculation to calculate and calculate the total delay time for each route from UE 10 to MEC 60, 90 based on the processing delay time in each MEC 60, 90 and the communication delay time from UE 10 to each MEC 60, 90.
  • the route connected from the UE 10 to the MECs 60 and 90 is switched so that the UE 10 is connected to the MEC having the shortest total delay time. It is characterized by including a route switching unit 42.
  • the relay device 40 calculates the total delay time DT1 (delay time of the first communication path) from the UE 10 to the MEC 60, and also from the UE 10 to the MEC 90.
  • the total delay time DT2 (delay time of the second communication path) is calculated.
  • the route switching unit 42 of the relay device 40 connects the UE 10 to the route of MEC60, 90 having the shortest total delay time among the calculated total delay times DT1 and DT2 for each MEC60,90 route. , The route from UE10 to MEC60,90 is switched.
  • the relay device 40 provides a low-delay service by dynamically switching the route of the MEC 60, 90 so as to connect the UE 10 to the MEC 60, 90 having the smallest delay amount. Can be done.
  • the distribution device 100 responds to a connection request from the UE 10 to the MEC 60 based on a communication delay from the distribution device 100 to the MEC 60, which is its own device, and a processing delay in the MEC 60.
  • the delay time from the distribution device 100 to the MEC60 is calculated, the communication delay from the distribution device 100 to the MEC90 different from the MEC60, and the processing delay in the MEC90 are calculated, and the delay time from the distribution device 100 to the MEC90 is calculated.
  • the time calculation unit 101 compares the delay time from the distribution device 100 to the MEC 60 and the delay time from the distribution device 100 to the MEC 90, and distributes the UE 10 so that the UE 10 is connected to the MEC having a short delay time. It is characterized by including a route switching unit 102 for switching a route from the device 100 to the MECs 60 and 90.
  • the distribution device 100 calculates the delay time DT3 (delay time of the third communication path) from the distribution device 100 to the MEC60, and the delay time DT4 (fourth) from the distribution device 100 to the MEC90. (Delay time of communication path) is calculated. Further, the route switching unit 102 of the distribution device 100 compares the delay time DT3 from the distribution device 100 to the MEC60 with the delay time DT4 from the distribution device 100 to the MEC90, and the MEC60, 90 having a short delay time. The route from the distribution device 100 to the MECs 60 and 90 is switched so that the UE 10 is connected to.
  • the distribution device 100 provides a low-delay service by dynamically switching the route of the MEC 60, 90 so as to connect the UE 10 to the MEC 60, 90 having the smallest delay amount. be able to.
  • Network system 10 UE (communication terminal) 30, 40, 70 Relay device 60, 90 MEC (computing resource) 41 Total delay time calculation unit 42 Route switching unit 100, 110 Distribution device 101 Delay time calculation unit 102 Route switching unit 120 Aggregation device 121 Calculation unit 122 Route determination unit

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

A relay device (40) is provided with: a total delay time calculation unit (41) that calculates communication delay times from a UE (10) to respective MECs (60), (90), calculates processing delay times in the respective MECs (60), (90), and calculates total delay times from the UE (10) to the respective MECs (60), (90) on the basis of the processing delay times in the respective MECs (60), (90) and the communication delay times to the respective MECs (60), (90); and a path switching unit (42) that switches a path so as to connect the UE (10) to a MEC of the shortest total delay time among the total delay times to the MECs (60), (90).

Description

中継装置、振分装置、中継装置の経路切替方法、振分装置の経路切替方法、及びプログラムRelay device, distribution device, route switching method of relay device, route switching method of distribution device, and program
　本発明は、中継装置、振分装置、中継装置の経路切替方法、振分装置の経路切替方法、及びプログラムに関する。 The present invention relates to a relay device, a distribution device, a route switching method of the relay device, a route switching method of the distribution device, and a program.
　近年、Multi-Access Edge Computing(以下、これをＭＥＣという)という概念が注目されている。ＭＥＣは、従来の中央集約的なアーキテクチャと異なり、コンピューティングリソースを企業やユーザにとって物理的に近い拠点に配置することにより、ネットワーク全体のトラヒック量を改善したり、低遅延化を実現する技術である(例えば、非特許文献１参照)。 In recent years, the concept of Multi-Access Edge Computing (hereinafter referred to as MEC) has been attracting attention. Unlike the conventional centralized architecture, MEC is a technology that improves the traffic volume of the entire network and realizes low latency by arranging computing resources at locations physically close to companies and users. (See, for example, Non-Patent Document 1).
　そして、５Ｇ ｍｏｂｉｌｅ ｎｅｔｗｏｒｋにおいて、ＭＥＣのコンピューティングリソースは、ユーザプレーン機能（ＵＰＦ：User Plane Function）に接続されたＤａｔａ Ｎｅｔｗｏｒｋに配備されている（例えば、非特許文献２参照）。これにより、ＭＥＣは、ＵＰＦの近くに配備され、ＵＰＦと共に、様々な配備パターンが可能となっている。 Then, in the 5G mobile network, the MEC computing resource is deployed in the Data Network connected to the user plane function (UPF: User Plane Function) (see, for example, Non-Patent Document 2). As a result, the MEC is deployed near the UPF, and together with the UPF, various deployment patterns are possible.
　５Ｇ ｎｅｔｗｏｒｋのＭＥＣにおいて、通信端末（ＵＥ：User Equipment）は、予め設定されたＵＰＦと通信を行い、ＵＰＦの近傍に配備されたコンピューティングリソース（ＭＥＣ）において計算処理等が実行される。 In the 5G network MEC, the communication terminal (UE: User Equipment) communicates with the preset UPF, and the computing resource (MEC) deployed in the vicinity of the UPF executes calculation processing and the like.
　しかしながら、そのコンピューティングリソースの使用率が高く、コンピューティングリソースでの処理が順番待ちになって遅延を生じる状況や、通信に何らかの障害が発生し、そのコンピューティングリソースが使用不能な状態が発生しても、ＵＥは、ＵＰＦの近傍に配備されているコンピューティングリソースに接続されてしまうので、ＭＥＣが実現しようとしている低遅延性が失われてしまう。 However, the usage rate of the computing resource is high, the processing in the computing resource is waiting in order and delay occurs, or some kind of communication failure occurs and the computing resource becomes unusable. However, since the UE is connected to the computing resource deployed in the vicinity of the UPF, the low latency that the MEC is trying to realize is lost.
　このような点に鑑みて本発明がなされたのであり、本発明は、コンピューティングリソースの使用率が高く、コンピューティングリソースでの処理が順番待ちになって遅延を生じる状況や、通信に何らかの障害が発生し、そのコンピューティングリソースが使用不能な状態が発生しても、最も遅延量の少ないコンピューティングリソースに通信端末を接続するように経路を動的に切り替え、低遅延なサービスを提供することを課題とする。 The present invention has been made in view of such a point, and the present invention has a high utilization rate of computing resources, a situation in which processing by computing resources is waiting in order and a delay occurs, or some kind of failure in communication. To provide a low-latency service by dynamically switching the route so that the communication terminal is connected to the computing resource with the least amount of delay even if the computing resource becomes unavailable. Is the subject.
　本発明に係る中継装置は、
　通信端末からコンピューティングリソースへの接続要求に対し、前記通信端末から当該通信端末と接続可能な各前記コンピューティングリソースまでの通信遅延時間を算出するともに、
　各前記コンピューティングリソースにおける処理遅延時間を算出し、各当該コンピューティングリソースにおける処理遅延時間と、前記通信端末から各前記コンピューティングリソースまでの通信遅延時間とに基づいて、前記通信端末から各前記コンピューティングリソースまでの経路ごとに総遅延時間を算出する総遅延時間算出部と、
　算出された各前記コンピューティングリソースまでの経路ごとの前記総遅延時間のうち、最も前記総遅延時間の短い前記コンピューティングリソースに前記通信端末が接続されるように、前記経路を切り替える経路切替部と、
　を備えることを特徴とする。 The relay device according to the present invention is
In response to a connection request from a communication terminal to a computing resource, the communication delay time from the communication terminal to each computing resource that can be connected to the communication terminal is calculated, and the communication delay time is calculated.
The processing delay time in each of the computing resources is calculated, and based on the processing delay time in each of the computing resources and the communication delay time from the communication terminal to each of the computing resources, each of the computing from the communication terminal. A total delay time calculation unit that calculates the total delay time for each route to the ing resource,
A route switching unit that switches the route so that the communication terminal is connected to the computing resource having the shortest total delay time among the calculated total delay times for each route to the computing resource. ,
It is characterized by having.
　本発明によれば、最も遅延量の少ないコンピューティングリソースに通信端末を接続するように経路を動的に切り替え、低遅延なサービスを提供することができる。 According to the present invention, it is possible to dynamically switch a route so as to connect a communication terminal to a computing resource having the least amount of delay, and to provide a service with low delay.
本実施形態に係る中継装置が配置されるネットワークシステムの通信経路の例を説明する図である。It is a figure explaining the example of the communication path of the network system in which the relay device which concerns on this embodiment is arranged. 第１の実施形態に係る中継装置が実行する経路切替処理（その１）の流れを示すフローチャートである。It is a flowchart which shows the flow of the route switching process (the 1) executed by the relay device which concerns on 1st Embodiment. 第２の実施形態に係る振分装置が配置されるネットワークシステムの通信経路の例を説明する図である。It is a figure explaining the example of the communication path of the network system in which the distribution apparatus which concerns on 2nd Embodiment is arranged. 第２の実施形態に係る振分装置が実行する経路切替処理（その２）の流れを示すフローチャートである。It is a flowchart which shows the flow of the route switching process (the 2) executed by the distribution apparatus which concerns on 2nd Embodiment. 第３の実施形態に係る集約装置が配置されるネットワークシステムの通信経路の例を説明する図である。It is a figure explaining the example of the communication path of the network system in which the aggregation device which concerns on 3rd Embodiment is arranged. 第１の実施形態に係る中継装置の機能、及び第２の実施形態に係る振分装置の機能を実現するコンピュータの一例を示すハードウェア構成図である。It is a hardware block diagram which shows an example of the computer which realizes the function of the relay apparatus which concerns on 1st Embodiment, and the function of the distribution apparatus which concerns on 2nd Embodiment. ５Ｇ ｍｏｂｉｌｅ ｎｅｔｗｏｒｋにおけるＭＥＣの概略構成を示したブロック図である。It is a block diagram which showed the schematic structure of MEC in 5G mobile network. ＭＥＣの物理的な配備の４つの例を示した説明図である。It is explanatory drawing which showed four examples of the physical deployment of MEC.
　次に、本発明を実施するための形態について説明する。まず、中継装置や振分装置を含むネットワークシステムの構成要素となるＭＥＣ（Multi-Access Edge Computing）について、説明する。 Next, a mode for carrying out the present invention will be described. First, MEC (Multi-Access Edge Computing), which is a component of a network system including a relay device and a distribution device, will be described.
＜ＭＥＣの概要＞ <Overview of MEC>
　図７は、従来技術である、５Ｇ ｍｏｂｉｌｅ ｎｅｔｗｏｒｋにおけるＭＥＣの概略構成（ネットワーク構造）を示したブロック図である。 FIG. 7 is a block diagram showing a schematic configuration (network structure) of a MEC in a 5G mobile network, which is a conventional technique.
　図７に示すように、ＵＥ（User Equipment）２０１、ＲＡＮ（Radio Access Network）２０２、ＡＭＦ（Access and Mobility Management Function）２０３、ＮＳＳＦ（Network Slice Selection Function）２０４、ＮＲＦ（Network Resource Function）２０５、ＵＤＭ（Unified Data Management）２０６、ＰＣＦ（Policy Control Function）２０７、ＮＥＦ（Network Exposure Function）２０８、ＡＵＳＦ（Authentication Server Function）２０９、ＳＭＦ（Session Management Function）２１０、ＰＣＦ（Policy Control Function）２１１、ＵＰＦ（User Plane Function）２１２、及びＭＥＣ（Multi-Access Edge Computing） Ｓｙｓｔｅｍ３００を備えて構成されている。なお、ＵＰＦ２１２は、ＭＥＣ Ｓｙｓｔｅｍ３００に設けられている。 As shown in FIG. 7, UE (User Equipment) 201, RAN (Radio Access Network) 202, AMF (Access and Mobility Management Function) 203, NSSF (Network Slice Selection Function) 204, NRF (Network Resource Function) 205, UDM. (Unified Data Management) 206, PCF (Policy Control Function) 207, NEF (Network Exposure Function) 208, AUSF (Authentication Server Function) 209, SMF (Session Management Function) 210, PCF (Policy Control Function) 211, UPF (User) It is configured to include a Plane Function) 212 and a MEC (Multi-Access Edge Computing) System 300. The UPF 212 is provided in the MECSystem 300.
　ＵＥ２０１は、通信端末（無線端末）を示している。ＲＡＮ２０２は、無線基地局及び無線回線制御装置などで構成されるネットワークを示している。ＡＭＦ２０３は、アクセス及びモビリティを管理する機能を示している。ＮＳＳＦ２０４は、ユーザに適したネットワークスライスインスタンスの選択を行う機能を示している。ＮＲＦ２０５は、ネットワーク機能とそれらが生成するサービスを登録する機能を示している。ＵＤＭ２０６は、ユーザとサブスクリプションに関連する多くのサービスを担当する機能を示している。ＰＣＦ２０７は、５Ｇシステムのポリシーと規則を制御する機能を示している。ＮＥＦ２０８は、サービスを公開するために集中化された地点として機能し、システムの外部から発信された全ての接続要求を承認する役割を示している。ＡＵＳＦ２０９は、認証に関連する手順を処理する機能を示している。ＳＭＦ２１０は、セッションを管理する機能を示している。ＰＣＦ２１１は、ＰＣＦ２０７と同様に、５Ｇのポリシーと規則を制御する機能を示している。ＵＰＦ２１２は、ユーザデータのパケットを転送する機能を示している。 UE201 indicates a communication terminal (wireless terminal). RAN202 shows a network composed of a radio base station, a radio line control device, and the like. AMF 203 shows the function of managing access and mobility. NSSF204 shows a function of selecting a network slice instance suitable for the user. NRF205 shows network functions and the ability to register the services they generate. UDM206 describes the functionality responsible for many services related to users and subscriptions. PCF207 demonstrates the ability to control policies and rules for 5G systems. The NEF 208 acts as a centralized point for publishing services and is responsible for approving all connection requests originating from outside the system. AUSF209 shows the ability to handle procedures related to authentication. The SMF210 shows a function of managing sessions. The PCF211, like the PCF207, exhibits the ability to control 5G policies and rules. UPF212 shows a function of forwarding a packet of user data.
　ＭＥＣ Ｓｙｓｔｅｍ３００は、ＭＥＣ Ｏｒｃｈｅｓｔｒａｔｏｒ３１１を有しており、ＭＥＣ Ｏｒｃｈｅｓｔｒａｔｏｒ３１１は、システムレベルの機能エンティティを構成する。また、ＭＥＣ Ｓｙｓｔｅｍ３００は、分散ホストレベルにおいて、ＭＥＣ Ｐｌａｔｆｏｒｍ Ｍａｎａｇｅｒ３２３が管理するＭＥＣ Ｐｌａｔｆｏｒｍ３２２により５Ｇのネットワークのアプリケーション機能として、サービスを提供する。ＭＥＣ Ｓｙｓｔｅｍ３００のＤａｔａ Ｎｅｔｗｏｒｋ３２１は、インターネットなどのサービスを提供するサーバが接続されたネットワークの総称である。Ｄａｔａ Ｎｅｔｗｏｒｋ３２１は、アプリケーション（ＡＰＰ）が配備されている特定のエリアにおいて、ＬＡ／ＤＮ（Local Area/Data Network）に接続するための支援が、５Ｇ コアネットワーク（Ｃｏｒｅ Ｎｅｔｗｏｒｋ）によりサポートされている。 The MECSystem300 has a MECOrchester311, which constitutes a system-level functional entity. Further, the MECSystem 300 provides a service as an application function of a 5G network by the MEC Platform 322 managed by the MEC Platform Manager 323 at the distributed host level. Data Network 321 of MECSystem300 is a general term for networks to which servers that provide services such as the Internet are connected. The Data Network 321 is supported by the 5G core network (CoreNetwork) to connect to the LA / DN (Local Area / Data Network) in a specific area where the application (APP) is deployed.
　これにより、５Ｇ ｍｏｂｉｌｅ ｎｅｔｗｏｒｋを構成するＭＥＣでは、ＭＥＣ Ｓｙｓｔｅｍ３００のＤａｔａ Ｎｅｔｗｏｒｋ３２１（ＬＡ／ＤＮ）にコンピューティングリソースを配備することにより、低遅延化を実現するようになっている。 As a result, in the MEC that constitutes the 5G mobile network, low latency is realized by deploying computing resources to the Data Network 321 (LA / DN) of the MEC System 300.
　ここで、ＵＰＦ２１２とＭＥＣのコンピューティングリソースを配備する場所は、比較的自由に決定することができる。例えば、ＭＥＣのコンピューティングリソースが接続されるＵＰＦ２１２は、基地局の近くに配備されてもよく、また、コアネットワーク内に配備されてもよい。 Here, the location where the UPF212 and MEC computing resources are deployed can be determined relatively freely. For example, the UPF212 to which the computing resources of the MEC are connected may be deployed near the base station or may be deployed in the core network.
　図８は、ＭＥＣ（コンピューティングリソース）の実際の物理的な配備の４つの例ＥＸ１～ＥＸ４を示した説明図である。なお、同一の構成については、同一の符号を付し、説明を適宜、省略する。 FIG. 8 is an explanatory diagram showing four examples EX1 to EX4 of actual physical deployment of MEC (computing resource). The same components are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
　図８の例ＥＸ１では、ＭＥＣ４２１とローカルのＵＰＦ４１１が基地局に配備された例を示している。図８に示すように、ＭＥＣ４２１は、基地局４０１と一緒に配備されたＵＰＦ４１１に接続されている。ＭＥＣ４２２は、基地局４０２と一緒に配備されたＵＰＦ４１２に接続されている。ＭＥＣ４２１，４２２は、ルータ４３１を介して、ＣＮ（Ｃｏｒｅ Ｎｅｔｗｏｒｋ）４４１に接続されている。 Example EX1 in FIG. 8 shows an example in which MEC421 and a local UPF411 are deployed at a base station. As shown in FIG. 8, the MEC421 is connected to the UPF411 deployed together with the base station 401. The MEC422 is connected to the UPF412 deployed together with the base station 402. The MEC 421 and 422 are connected to the CN (Core Network) 441 via the router 431.
　図８の例ＥＸ２では、ＭＥＣ４２１がローカルのＵＰＦ４１１と共に、伝送ノードに配備された例を示している。なお、基地局４０１は、ＵＰＦ４１１に接続され、基地局４０３は、ＭＥＣ４２１に接続されている。ＵＰＦ４１１及びＭＥＣ４２１は、ルータ４３１を介して、ＣＮ４４１に接続されている。 Example EX2 in FIG. 8 shows an example in which MEC421 is deployed at a transmission node together with a local UPF411. The base station 401 is connected to UPF411, and the base station 403 is connected to MEC421. UPF411 and MEC421 are connected to CN441 via router 431.
　図８の例ＥＸ３では、ＭＥＣ４２１とローカルのＵＰＦ４１１が一体としてネットワークに配備された例を示している。ＭＥＣ４２１とローカルのＵＰＦ４１１は、一体としてルータ４３１を介してＣＮ４４１に接続されている。基地局４０１，４０２，４０３は、ルータ４３１に接続されている。 Example EX3 in FIG. 8 shows an example in which MEC421 and the local UPF411 are integrated and deployed in the network. The MEC421 and the local UPF411 are integrally connected to the CN441 via the router 431. The base stations 401, 402, and 403 are connected to the router 431.
　図８の例ＥＸ４では、ＭＥＣ４２１，４２２が同じデータセンタのコアネットワークに配備された例を示している。ＭＥＣ４２１は、ＣＮ４４１内にあるＵＰＦ４１１に接続されており、ＭＥＣ４２２は、ＣＮ４４１内にあるＵＰＦ４１２に接続されている。 Example EX4 in FIG. 8 shows an example in which MEC421 and 422 are deployed in the core network of the same data center. The MEC421 is connected to the UPF411 in the CN441, and the MEC422 is connected to the UPF412 in the CN441.
　このように、ＭＥＣ４２１，４２２に接続されるＵＰＦ４１１，４１２は、基地局の近くに配備されてもよく、また、コアネットワーク内に配備されていてもよい。 In this way, the UPF411,412 connected to the MEC421,422 may be deployed near the base station, or may be deployed in the core network.
　ここで、例えば、東京、大阪の２か所で事業を行う企業があったとき、東京にある通信端末は、通常、東京のＭＥＣに接続されるように設定されている。しかしながら、東京の拠点のＭＥＣにおいて通信遅延が大きい場合、その東京にある通信端末は、大阪の拠点のＭＥＣに接続した方が通信遅延を抑えられることがある。例えば、東京と大阪のＭＥＣがパブリッククラウドや専用線などで接続されており、通信端末における処理が東京と大阪のいずれのＭＥＣでも処理が可能な場合、実現可能である。 Here, for example, when there are companies operating in two locations, Tokyo and Osaka, the communication terminal in Tokyo is usually set to be connected to the MEC in Tokyo. However, when the communication delay is large in the MEC of the base in Tokyo, the communication terminal in the communication terminal in Tokyo may be suppressed by connecting to the MEC of the base in Osaka. For example, it is feasible when the MECs of Tokyo and Osaka are connected by a public cloud or a dedicated line, and the processing on the communication terminal can be processed by either the MECs of Tokyo and Osaka.
　図８の例ＥＸ１では、不図示のＵＥは、基地局４０１とＵＰＦ４１１を介して、ＭＥＣ４２１に接続される。ここで、例えば、ＭＥＣ４２１を東京の拠点に設置されたサーバとし、ＭＥＣ４２２を大阪の拠点に設置されたサーバとする。 In the example EX1 of FIG. 8, the UE (not shown) is connected to the MEC421 via the base station 401 and the UPF411. Here, for example, MEC421 is a server installed at a base in Tokyo, and MEC422 is a server installed at a base in Osaka.
　そして、東京の拠点に設置されたＭＥＣ４２１は、コンピューティングリソースの使用率が高く、処理待ちのため遅延が生じている状況であると仮定する。一方、大阪の拠点に設置されたＭＥＣ４２２は、コンピューティングリソースの使用率が低く、通信遅延が低い状況であると仮定する。 Then, it is assumed that the MEC421 installed at the base in Tokyo has a high utilization rate of computing resources and is in a situation where there is a delay due to waiting for processing. On the other hand, it is assumed that the MEC422 installed at the base in Osaka has a low computing resource usage rate and a low communication delay.
　この場合、基地局４０１に接続されたＵＥ（不図示）は、東京の拠点に設置されたＭＥＣ４２１に接続されるが、ＭＥＣ４２１において通信遅延や処理遅延が大きい場合には、ルータ４３１及びＵＰＦ４１２を介して、大阪の拠点に設置されたＭＥＣ４２２に接続し、通信遅延や処理遅延を回避することが望まれる。 In this case, the UE (not shown) connected to the base station 401 is connected to the MEC421 installed at the base in Tokyo, but if the communication delay or the processing delay is large in the MEC421, the router 431 and the UPF412 are used. Therefore, it is desirable to connect to the MEC422 installed at the base in Osaka to avoid communication delays and processing delays.
　そこで、本発明の第１の実施形態に係る中継装置（図１参照）は、総遅延時間算出部と、経路切替部とを備え、各コンピューティングリソース（ＭＥＣ）までの経路ごとの遅延時間のうち、最も遅延時間の短いコンピューティングリソース（ＭＥＣ）にＵＥが接続されるように、ＵＥがコンピューティングリソース（ＭＥＣ）に接続される経路を切り替えることを特徴とする。 Therefore, the relay device (see FIG. 1) according to the first embodiment of the present invention includes a total delay time calculation unit and a route switching unit, and has a delay time for each route to each computing resource (MEC). Among them, the UE is characterized by switching the route connected to the computing resource (MEC) so that the UE is connected to the computing resource (MEC) having the shortest delay time.
　また、本発明の第２の実施形態に係る振分装置（図３参照）は、遅延時間算出部と、経路切替部とを備え、自装置から第１のコンピューティングリソース（ＭＥＣ）までの遅延時間と、自装置から第２のコンピューティングリソース（ＭＥＣ）までの遅延時間とを比較して、遅延時間の短いコンピューティングリソース（ＭＥＣ）にＵＥが接続されるように、自装置から第１又は第２のコンピューティングリソース（ＭＥＣ）までの経路を切り替えることを特徴とする。 Further, the distribution device (see FIG. 3) according to the second embodiment of the present invention includes a delay time calculation unit and a route switching unit, and delays from the own device to the first computing resource (MEC). The time is compared with the delay time from the own device to the second computing resource (MEC) so that the UE is connected to the computing resource (MEC) having the shorter delay time from the own device to the first or second computing resource (MEC). It is characterized by switching the route to the second computing resource (MEC).
　これにより、第１の実施形態に係る中継装置、及び第２の実施形態に係る振分装置は、最も遅延量の少ないコンピューティングリソース（ＭＥＣ）にＵＥを接続するように経路を動的に切り替え、低遅延なサービスを提供することができる。 As a result, the relay device according to the first embodiment and the distribution device according to the second embodiment dynamically switch the route so as to connect the UE to the computing resource (MEC) having the least delay amount. , Can provide low latency service.
＜第１の実施形態＞
　第１の実施形態に係る中継装置（図１参照）は、通信端末からコンピューティングリソースへの接続要求に対し、通信端末から当該通信端末と接続可能な各コンピューティングリソースまでの通信遅延時間を算出するともに、各コンピューティングリソースにおける処理遅延時間を算出し、各当該コンピューティングリソースにおける処理遅延時間と、通信端末から各コンピューティングリソースまでの通信遅延時間とに基づいて、通信端末から各コンピューティングリソースまでの経路ごとに総遅延時間を算出する総遅延時間算出部と、算出された各コンピューティングリソースまでの経路ごとの総遅延時間のうち、最も総遅延時間の短いコンピューティングリソースに通信端末が接続されるように、経路を切り替える経路切替部と、を備えている。 <First Embodiment>
The relay device according to the first embodiment (see FIG. 1) calculates the communication delay time from the communication terminal to each computing resource that can connect to the communication terminal in response to the connection request from the communication terminal to the computing resource. At the same time, the processing delay time for each computing resource is calculated, and each computing resource from the communication terminal is based on the processing delay time for each computing resource and the communication delay time from the communication terminal to each computing resource. The communication terminal connects to the computing resource with the shortest total delay time among the total delay time calculation unit that calculates the total delay time for each route to and the calculated total delay time for each route to each computing resource. It is provided with a route switching unit for switching routes so as to be performed.
　図１は、第１実施形態に係る中継装置４０が配置されるネットワークシステム５００の通信経路の例を説明する図である。 FIG. 1 is a diagram illustrating an example of a communication path of the network system 500 in which the relay device 40 according to the first embodiment is arranged.
　図１に示すように、ネットワークシステム５００は、ＵＥ（User Equipment：通信端末）１０、基地局２０、中継装置３０、中継装置４０、ＵＰＦ（User Plane Function：ユーザプレーン機能）５０、ＭＥＣ（Multi-Access Edge Computing）６０、中継装置７０、ＵＰＦ８０、及びＭＥＣ９０を備えて構成されている。図１では、ネットワークシステム５００は、ＵＥ１０からＭＥＣ６０までの通信経路（第１の通信経路）と、ＵＥ１０からＭＥＣ９０までの通信経路（第２の通信経路）とを備えて構成されている。 As shown in FIG. 1, the network system 500 includes a UE (User Equipment: communication terminal) 10, a base station 20, a relay device 30, a relay device 40, an UPF (User Plane Function) 50, and a MEC (Multi-). Access Edge Computing) 60, relay device 70, UPF80, and MEC90 are provided. In FIG. 1, the network system 500 includes a communication path from the UE 10 to the MEC 60 (first communication path) and a communication path from the UE 10 to the MEC 90 (second communication path).
　第１の通信経路は、ＵＥ１０、基地局２０、中継装置３０、中継装置４０、ＵＰＦ５０、及びＭＥＣ６０の通信経路で構成されている。第２の通信経路は、ＵＥ１０、基地局２０、中継装置３０、中継装置４０、中継装置７０、ＵＰＦ８０、及びＭＥＣ９０の通信経路で構成されている。まず、第１の通信経路について、説明する。 The first communication path is composed of the communication path of the UE 10, the base station 20, the relay device 30, the relay device 40, the UPF50, and the MEC60. The second communication path is composed of the communication path of the UE 10, the base station 20, the relay device 30, the relay device 40, the relay device 70, the UPF80, and the MEC90. First, the first communication path will be described.
　ＵＥ１０は、ユーザが使用する通信端末（無線端末）を示している。 UE 10 indicates a communication terminal (wireless terminal) used by the user.
　基地局２０は、ＵＥ１０との無線区間を接続し、終端する装置である。なお、ＵＥ１０から基地局２０までの通信遅延を、Δａとする。 The base station 20 is a device that connects and terminates a wireless section with the UE 10. The communication delay from the UE 10 to the base station 20 is defined as Δa.
　中継装置３０，４０は、基地局２０からＵＰＦ５０までの間のネットワークを中継する装置である。なお、基地局２０から中継装置３０までの通信遅延を、Δｂとする。また、中継装置３０から中継装置４０までの通信遅延を、Δｃとする。 The relay devices 30 and 40 are devices that relay the network between the base station 20 and the UPF 50. The communication delay from the base station 20 to the relay device 30 is defined as Δb. Further, the communication delay from the relay device 30 to the relay device 40 is defined as Δc.
　また、中継装置３０，４０は、総遅延時間算出部４１と、経路切替部４２とを備えて構成されている。なお、以下の説明では、一例として、中継装置４０を用いて説明する。 Further, the relay devices 30 and 40 are configured to include a total delay time calculation unit 41 and a route switching unit 42. In the following description, the relay device 40 will be used as an example.
　総遅延時間算出部４１は、ＵＥ１０からＭＥＣ６０への接続要求に対し、ＵＥ１０から当該ＵＥ１０と接続可能な各ＭＥＣ６０，９０までの通信遅延時間を算出するともに、各ＭＥＣ６０，９０における処理遅延時間を算出し、各ＭＥＣ６０，９０における処理遅延時間と、ＵＥ１０から各ＭＥＣ６０，９０までの通信遅延時間とに基づいて、ＵＥ１０から各ＭＥＣ６０，９０までの経路ごとに総遅延時間を算出する機能を有している。 The total delay time calculation unit 41 calculates the communication delay time from the UE 10 to each MEC60, 90 that can connect to the UE 10 in response to the connection request from the UE 10 to the MEC60, and also calculates the processing delay time in each MEC60, 90. It also has a function to calculate the total delay time for each route from UE 10 to MEC 60, 90 based on the processing delay time in each MEC 60, 90 and the communication delay time from UE 10 to each MEC 60, 90. There is.
　経路切替部４２は、算出された各ＭＥＣ６０，９０までの経路ごとの総遅延時間のうち、最も総遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続されるように、ＵＥ１０がＭＥＣ６０，９０に接続される経路を切り替える機能を有している。 The route switching unit 42 connects the UE 10 to the MEC 60, 90 so that the UE 10 is connected to the MEC 60, 90 having the shortest total delay time among the calculated total delay times for each MEC 60, 90. It has a function to switch the route.
　ＵＰＦ５０は、基地局２０からＭＥＣ６０までユーザデータのパケットを転送する機能を有している。ＵＰＦ５０は、例えば、データパケットの転送を担うルータとして機能する。なお、中継装置４０からＵＰＦ５０までの通信遅延を、Δｄとする。 The UPF 50 has a function of transferring a packet of user data from the base station 20 to the MEC 60. The UPF 50 functions as, for example, a router responsible for forwarding data packets. The communication delay from the relay device 40 to the UPF 50 is defined as Δd.
　ＭＥＣ６０は、低遅延を実現する技術であり、ＵＰＦ５０の付近に配備されるサーバ（コンピューティングリソース）である。なお、ＵＰＦ５０からＭＥＣ６０までの通信遅延を、Δｅとする。また、ＭＥＣ６０における処理遅延（処理遅延時間）を、Δαとする。 MEC60 is a technology that realizes low latency, and is a server (computing resource) deployed in the vicinity of UPF50. The communication delay from UPF50 to MEC60 is defined as Δe. Further, the processing delay (processing delay time) in MEC60 is defined as Δα.
　次に、第２の通信経路は、ＵＥ１０、基地局２０、中継装置３０、中継装置４０、中継装置７０、ＵＰＦ８０、及びＭＥＣ９０で構成されている。第１の通信経路と同一の構成については、同一の符号を付し、説明を適宜、省略する。 Next, the second communication path is composed of the UE 10, the base station 20, the relay device 30, the relay device 40, the relay device 70, the UPF80, and the MEC90. The same components as those of the first communication path are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
　第２の通信経路は、ＵＥ１０から中継装置４０まで、第１の通信経路と同一の通信経路を備えて構成されている。 The second communication path is configured to include the same communication path as the first communication path from the UE 10 to the relay device 40.
　中継装置７０は、中継装置３０，４０と同一の構成を備える中継装置である。なお、中継装置４０から中継装置７０までの通信遅延を、Δｆとする。 The relay device 70 is a relay device having the same configuration as the relay devices 30 and 40. The communication delay from the relay device 40 to the relay device 70 is defined as Δf.
　ＵＰＦ８０は、基地局２０からＭＥＣ９０までユーザデータのパケットを転送する機能を有している。ＵＰＦ８０は、ＵＰＦ５０と同一の構成を備える装置である。なお、中継装置７０からＵＰＦ８０までの通信遅延を、Δｇとする。 The UPF80 has a function of transferring a packet of user data from the base station 20 to the MEC90. The UPF80 is a device having the same configuration as the UPF50. The communication delay from the relay device 70 to the UPF80 is defined as Δg.
　ＭＥＣ９０は、ＭＥＣ６０と同一の構成を備えており、ＵＰＦ８０の付近に配備されるサーバ（コンピューティングリソース）である。なお、ＵＰＦ８０からＭＥＣ９０までの通信遅延を、Δｈとする。また、ＭＥＣ９０における処理遅延（処理遅延時間）を、Δβとする。 The MEC90 has the same configuration as the MEC60, and is a server (computing resource) deployed in the vicinity of the UPF80. The communication delay from UPF80 to MEC90 is defined as Δh. Further, the processing delay (processing delay time) in MEC90 is defined as Δβ.
　上述した通信遅延を示すΔａ～Δｈは、各通信区間の経路長、伝送容量、パケット長等のパラメータをもとに算出される。 The above-mentioned communication delays Δa to Δh are calculated based on parameters such as the path length, transmission capacity, and packet length of each communication section.
　また、上述した処理遅延（処理遅延時間）を示すΔα及びΔβは、各ＭＥＣ６０，９０における遅延量を示しており、例えば、各サーバのＣＰＵ（Central Processing Unit）処理待ちキュー数やＣＰＵ切り替え時に生じるコンテキストスイッチ数、パケットの受信キュー数、遅延測定用パケットによる遅延量測定結果等をもとに算出される。なお、通信遅延及び処理遅延（処理遅延時間）は、直近の遅延の変化の傾向（例えば、遅延時間が増加傾向にある等）を加味してもよい。 Further, Δα and Δβ indicating the above-mentioned processing delay (processing delay time) indicate the delay amount in each MEC 60, 90, and are generated, for example, the number of CPU (Central Processing Unit) processing wait queues of each server or when the CPU is switched. It is calculated based on the number of context switches, the number of packet reception queues, the delay amount measurement result of the delay measurement packet, and the like. The communication delay and the processing delay (processing delay time) may take into account the tendency of the latest delay change (for example, the delay time tends to increase).
　第１の実施形態では、中継装置３０，４０，７０は、ＵＥ１０から送信されるパケット、又はユーザの契約情報に基づいた事前の設定により、ＵＥ１０に関連するＭＥＣ６０，９０が、どのＵＰＦ５０，８０に収容されているか、事前に設定されているものとする。 In the first embodiment, in the relay device 30, 40, 70, the MEC60, 90 related to the UE 10 is set to which UPF 50, 80 by the packet transmitted from the UE 10 or the preset setting based on the contract information of the user. It shall be contained or preset.
　また、中継装置３０，４０，７０と、ＵＰＦ５０，８０と、ＭＥＣ６０，９０とは、常に互いに通信しており、中継装置３０，４０，７０は、通信遅延のΔａ～Δｈ、処理遅延（処理遅延時間）のΔα及びΔβの全ての値を記憶している。なお、ＵＥ１０は、事前の設定により、ＭＥＣ６０に接続されるように設定されているものとする。 Further, the relay devices 30, 40, 70, the UPF 50, 80, and the MEC 60, 90 are always communicating with each other, and the relay devices 30, 40, 70 have communication delays Δa to Δh and processing delays (processing delays). All values of Δα and Δβ of (time) are stored. It is assumed that the UE 10 is set to be connected to the MEC 60 by a prior setting.
＜第１の実施形態の処理の流れ＞
　次に、第１の実施形態に係る中継装置４０が実行する処理の流れについて説明する。 <Flow of processing of the first embodiment>
Next, the flow of processing executed by the relay device 40 according to the first embodiment will be described.
≪経路切替処理（その１）≫
　図２は、第１の実施形態に係る中継装置４０が実行する経路切替処理の流れを示すフローチャートである。 ≪Route switching process (1) ≫
FIG. 2 is a flowchart showing the flow of the route switching process executed by the relay device 40 according to the first embodiment.
　まず、ＵＥ１０からＭＥＣ６０への接続要求が送信されると、中継装置４０は、ＵＥ１０からＭＥＣ６０までの総遅延時間ＤＴ１（第１の通信経路の遅延時間）を算出する（ステップＳ００１）。 First, when the connection request from the UE 10 to the MEC 60 is transmitted, the relay device 40 calculates the total delay time DT1 (delay time of the first communication path) from the UE 10 to the MEC 60 (step S001).
　具体的には、中継装置４０の総遅延時間算出部４１は、ＵＥ１０に接続される基地局２０の通信遅延のΔａ、基地局２０に接続される中継装置３０の通信遅延のΔｂ、中継装置３０に接続される中継装置４０の通信遅延のΔｃ、中継装置４０に接続されるＵＰＦ５０の通信遅延のΔｄ、及びＵＰＦ５０に接続されるＭＥＣ６０の通信遅延のΔｅの合計通信遅延時間（Δａ～Δｅの和）を算出する。また、総遅延時間算出部４１は、ＭＥＣ６０における処理遅延時間のΔαを算出し、ＭＥＣ６０における処理遅延時間のΔαと、ＭＥＣ６０までの合計通信遅延時間（Δａ～Δｅの和）とに基づいて、ＵＥ１０からＭＥＣ６０までの総遅延時間ＤＴ１（Δａ～Δｅの和＋Δα）を算出する。 Specifically, the total delay time calculation unit 41 of the relay device 40 has Δa of the communication delay of the base station 20 connected to the UE 10, Δb of the communication delay of the relay device 30 connected to the base station 20, and the relay device 30. The total communication delay time (sum of Δa to Δe) of the communication delay Δc of the relay device 40 connected to the relay device 40, the communication delay Δd of the UPF 50 connected to the relay device 40, and the communication delay Δe of the MEC 60 connected to the UPF 50. ) Is calculated. Further, the total delay time calculation unit 41 calculates the processing delay time Δα in the MEC60, and based on the processing delay time Δα in the MEC60 and the total communication delay time (sum of Δa to Δe) up to the MEC60, the UE 10 The total delay time DT1 (sum of Δa to Δe + Δα) from to MEC60 is calculated.
　次に、中継装置４０は、ＵＥ１０からＭＥＣ９０までの総遅延時間ＤＴ２（第２の通信経路の遅延時間）を算出する（ステップＳ００３）。 Next, the relay device 40 calculates the total delay time DT2 (delay time of the second communication path) from the UE 10 to the MEC 90 (step S003).
　具体的には、中継装置４０の総遅延時間算出部４１は、ＵＥ１０に接続される基地局２０の通信遅延のΔａ、基地局２０に接続される中継装置３０の通信遅延のΔｂ、中継装置３０に接続される中継装置４０の通信遅延のΔｃ、中継装置４０に接続される中継装置７０の通信遅延のΔｆ、中継装置７０に接続されるＵＰＦ８０の通信遅延のΔｇ、ＵＰＦ８０に接続されるＭＥＣ９０の通信遅延のΔｈの合計通信遅延時間（Δａ～Δｈの和）を算出する。また、総遅延時間算出部４１は、ＭＥＣ９０における処理遅延時間のΔβを算出し、ＭＥＣ９０における処理遅延時間のΔβと、ＭＥＣ９０までの合計通信遅延時間（Δａ～Δｈの和）とに基づいて、ＵＥ１０からＭＥＣ９０までの総遅延時間ＤＴ２（Δａ～Δｈの和＋Δβ）を算出する。 Specifically, the total delay time calculation unit 41 of the relay device 40 has Δa of the communication delay of the base station 20 connected to the UE 10, Δb of the communication delay of the relay device 30 connected to the base station 20, and the relay device 30. The communication delay Δc of the relay device 40 connected to the relay device 40, the communication delay Δf of the relay device 70 connected to the relay device 40, the communication delay Δg of the UPF 80 connected to the relay device 70, and the MEC 90 connected to the UPF 80. The total communication delay time (sum of Δa to Δh) of Δh of the communication delay is calculated. Further, the total delay time calculation unit 41 calculates the processing delay time Δβ in the MEC 90, and based on the processing delay time Δβ in the MEC 90 and the total communication delay time (the sum of Δa to Δh) up to the MEC 90, the UE 10 The total delay time DT2 (sum of Δa to Δh + Δβ) from to MEC90 is calculated.
　そして、中継装置４０は、第１の通信経路の総遅延時間ＤＴ１が、第２の通信経路の総遅延時間ＤＴ２以下か否かを判定し（ステップＳ００５）、総遅延時間ＤＴ１が総遅延時間ＤＴ２以下の場合（ステップＳ００５のＹｅｓ）、ＭＥＣ６０での処理は適切であると判定し、ＵＥ１０をＭＥＣ６０に接続して（ステップＳ００７）、経路切替処理を終了する。 Then, the relay device 40 determines whether or not the total delay time DT1 of the first communication path is equal to or less than the total delay time DT2 of the second communication path (step S005), and the total delay time DT1 is the total delay time DT2. In the following case (Yes in step S005), it is determined that the processing in MEC60 is appropriate, the UE 10 is connected to MEC60 (step S007), and the route switching processing is terminated.
　一方、第１の通信経路の総遅延時間ＤＴ１が、第２の通信経路の総遅延時間ＤＴ２より大きい場合（ステップＳ００５のＮｏ）、ＭＥＣ６０で処理するよりもＭＥＣ９０で処理した方が、総遅延時間が短いため、中継装置４０は、ＵＥ１０がＭＥＣ９０に接続されるように経路を切り替えて（ステップＳ００９）、処理を終了する。 On the other hand, when the total delay time DT1 of the first communication path is larger than the total delay time DT2 of the second communication path (No in step S005), the total delay time is processed by MEC90 rather than by MEC60. The relay device 40 switches the route so that the UE 10 is connected to the MEC 90 (step S009), and ends the process.
　このように、中継装置４０の経路切替部４２は、算出された各ＭＥＣ６０，９０の経路ごとの総遅延時間のうち、最も総遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続されるように、ＵＥ１０がＭＥＣ６０，９０に接続される経路を切り替える。 In this way, the route switching unit 42 of the relay device 40 connects the UE 10 to the MEC 60, 90 having the shortest total delay time among the calculated total delay times for each route of the MEC 60, 90. Switches the route connected to MEC60,90.
　以上説明したように、第１の実施形態によれば、中継装置４０は、最も遅延量（例えば、総遅延時間）の少ないＭＥＣに接続するようにＭＥＣの経路を動的に切り替えることにより、低遅延なサービスを提供することができる。 As described above, according to the first embodiment, the relay device 40 is low by dynamically switching the path of the MEC so as to connect to the MEC having the smallest delay amount (for example, total delay time). It is possible to provide delayed service.
　なお、第１の実施形態では、中継装置４０の総遅延時間算出部４１が総遅延時間を算出し、経路切替部４２がＵＥ１０からＭＥＣ６０，９０までの経路を切り替えるようになっていたが、これに限定されるものではない。例えば、第１の実施形態では、中継装置４０の総遅延時間算出部４１の代わりに中継装置７０が総遅延時間を算出し、その総遅延時間に基づいて、中継装置４０の経路切替部４２が、ＭＥＣ６０，９０への経路を動的に切り替えてもよい。 In the first embodiment, the total delay time calculation unit 41 of the relay device 40 calculates the total delay time, and the route switching unit 42 switches the route from the UE 10 to the MEC 60, 90. Not limited to. For example, in the first embodiment, the relay device 70 calculates the total delay time instead of the total delay time calculation unit 41 of the relay device 40, and the route switching unit 42 of the relay device 40 calculates the total delay time based on the total delay time. , MEC60, 90 may be dynamically switched.
　また、第１の実施形態において、中継装置４０の経路切替部４２が、ＵＥ１０の経路を第１の通信経路から第２の通信経路に切り換えた場合、更に、中継装置７０が総遅延時間を算出し、その総遅延時間に基づいて、中継装置４０の経路切替部４２が、ＵＥ１０からＭＥＣ６０，９０までの経路を切り替えてもよい。 Further, in the first embodiment, when the route switching unit 42 of the relay device 40 switches the route of the UE 10 from the first communication path to the second communication path, the relay device 70 further calculates the total delay time. Then, the route switching unit 42 of the relay device 40 may switch the route from the UE 10 to the MECs 60 and 90 based on the total delay time.
　また、同様に、中継装置３０が中継装置４０の総遅延時間算出部４１の代わりに総遅延時間を算出してもよく、その総遅延時間に基づいて、中継装置４０の経路切替部４２が、ＵＥ１０からＭＥＣ６０，９０までの経路を切り替えてもよい。 Similarly, the relay device 30 may calculate the total delay time instead of the total delay time calculation unit 41 of the relay device 40, and the route switching unit 42 of the relay device 40 may calculate the total delay time based on the total delay time. The route from UE 10 to MEC 60, 90 may be switched.
＜第２の実施形態＞
　第２の実施形態に係る振分装置（図３参照）は、通信端末から第１のコンピューティングリソースへの接続要求に対し、自装置である振分装置から第１のコンピューティングリソースまでの通信遅延と、当該第１のコンピューティングリソースにおける処理遅延とに基づいて、自装置から第１のコンピューティングリソースまでの遅延時間を算出するとともに、自装置から第１のコンピューティングリソースとは異なる第２のコンピューティングリソースまでの通信遅延と、当該第２のコンピューティングリソースにおける処理遅延とを算出し、自装置から第２のコンピューティングリソースまでの遅延時間を算出する遅延時間算出部と、自装置から第１のコンピューティングリソースまでの遅延時間と、自装置から第２のコンピューティングリソースまでの遅延時間とを比較して、遅延時間の短いコンピューティングリソースに通信端末が接続されるように、自装置から第１又は第２のコンピューティングリソースまでの経路を切り替える経路切替部と、を備えている。 <Second embodiment>
The distribution device according to the second embodiment (see FIG. 3) communicates from the distribution device, which is its own device, to the first computing resource in response to a connection request from the communication terminal to the first computing resource. Based on the delay and the processing delay in the first computing resource, the delay time from the own device to the first computing resource is calculated, and the second device different from the first computing resource is calculated. The delay time calculation unit that calculates the communication delay to the computing resource of the above and the processing delay in the second computing resource, and calculates the delay time from the own device to the second computing resource, and the own device. The delay time to the first computing resource is compared with the delay time from the own device to the second computing resource, and the own device is connected so that the communication terminal is connected to the computing resource having the shorter delay time. It is provided with a route switching unit for switching a route from the first to the first or second computing resource.
　図３は、第２の実施形態に係る振分装置１００が配置されるネットワークシステム５０１の通信経路の例を説明する図である。ネットワークシステム５０１は、ネットワークシステム５００と異なり、ＵＰＦ５０とＭＥＣ６０との間に、振分装置１００を備えて構成されている。また同様に、ネットワークシステム５０１は、ＵＰＦ８０とＭＥＣ９０の間に、振分装置１１０を備えて構成されている。 FIG. 3 is a diagram illustrating an example of a communication path of the network system 501 in which the distribution device 100 according to the second embodiment is arranged. Unlike the network system 500, the network system 501 is configured to include a distribution device 100 between the UPF 50 and the MEC 60. Similarly, the network system 501 is configured to include a distribution device 110 between the UPF 80 and the MEC 90.
　図３に示すように、ネットワークシステム５０１は、ＵＥ１０、基地局２０、中継装置３０、中継装置４０、ＵＰＦ５０、振分装置１００、ＭＥＣ６０、中継装置７０、ＵＰＦ８０、振分装置１１０、及びＭＥＣ９０を備えて構成されている。図３では、ネットワークシステム５０１は、振分装置１００からＭＥＣ６０までの通信経路（第３の通信経路）と、振分装置１００からＭＥＣ９０までの通信経路（第４の通信経路）とを備えている。なお、第１の実施形態と同一の構成については同一の符号を付し、説明を適宜、省略する。 As shown in FIG. 3, the network system 501 includes a UE 10, a base station 20, a relay device 30, a relay device 40, an UPF 50, a distribution device 100, a MEC 60, a relay device 70, an UPF 80, a distribution device 110, and a MEC 90. It is composed of. In FIG. 3, the network system 501 includes a communication path from the distribution device 100 to the MEC60 (third communication path) and a communication path from the distribution device 100 to the MEC90 (fourth communication path). .. The same components as those in the first embodiment are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
　また、第２の実施形態では、一例として、振分装置１００，１１０が、ＵＰＦ５０，８０とＭＥＣ６０,９０の間に配置されているが、これに限定されるものではない。例えば、第２の実施形態に係る振分装置１００，１１０の機能をＵＰＦ５０，８０に設け、ＵＰＦ５０，８０が振分装置１００，１１０と同様な処理を実行してもよく、また、振分装置１００，１１０の機能をＭＥＣ６０,９０に設け、ＭＥＣ６０,９０が振分装置１００，１１０と同様な処理を実行してもよい。 Further, in the second embodiment, as an example, the distribution devices 100 and 110 are arranged between the UPF 50 and 80 and the MEC 60 and 90, but the present invention is not limited to this. For example, the functions of the distribution devices 100 and 110 according to the second embodiment may be provided in the UPFs 50 and 80, and the UPFs 50 and 80 may perform the same processing as the distribution devices 100 and 110, or the distribution devices may be executed. The functions of 100 and 110 may be provided in the MECs 60 and 90, and the MECs 60 and 90 may execute the same processing as the distribution devices 100 and 110.
　第３の通信経路は、振分装置１００及びＭＥＣ６０で構成されている。第４の通信経路は、振分装置１００、ＵＰＦ５０、中継装置４０、中継装置７０、ＵＰＦ８０、振分装置１１０、及びＭＥＣ９０で構成されている。 The third communication path is composed of the distribution device 100 and the MEC60. The fourth communication path is composed of a distribution device 100, an UPF 50, a relay device 40, a relay device 70, an UPF 80, a distribution device 110, and a MEC 90.
　なお、第２の実施形態では、ＵＰＦ５０から振分装置１００までの通信遅延を、Δｅとし、振分装置１００からＭＥＣ６０までの通信遅延を、Δｉとする。また、ＵＰＦ８０から振分装置１１０までの通信遅延を、Δｈとし、振分装置１１０からＭＥＣ９０までの通信遅延を、Δｊとする。 In the second embodiment, the communication delay from the UPF 50 to the distribution device 100 is Δe, and the communication delay from the distribution device 100 to the MEC 60 is Δi. Further, the communication delay from the UPF 80 to the distribution device 110 is defined as Δh, and the communication delay from the distribution device 110 to the MEC 90 is defined as Δj.
　第２の実施形態に係る振分装置１００、１１０が、第１の実施形態と異なる点は、振分装置１００、１１０のみが、中継装置３０，４０，７０、ＵＰＦ５０，８０、及びＭＥＣ６０，９０と通信し、通信遅延を示すΔａ～Δｊと、処理遅延（処理遅延時間）を示すΔα及びΔβの値を記憶する。そのため、中継装置３０，４０，７０と、ＵＰＦ５０，８０と、ＭＥＣ６０，９０は、互いに通信する必要はない。 The distribution devices 100 and 110 according to the second embodiment are different from the first embodiment only in the distribution devices 100 and 110, the relay devices 30, 40, 70, UPF 50, 80, and MEC 60, 90. And stores Δa to Δj indicating a communication delay and values of Δα and Δβ indicating a processing delay (processing delay time). Therefore, the relay devices 30, 40, 70, UPF 50, 80, and MEC 60, 90 do not need to communicate with each other.
　また、振分装置１００，１１０は、遅延時間算出部１０１と、経路切替部１０２とを備えて構成されている。なお、以下の説明では、一例として、振分装置１００を用いて説明する。 Further, the distribution devices 100 and 110 are configured to include a delay time calculation unit 101 and a route switching unit 102. In the following description, the sorting device 100 will be used as an example.
　遅延時間算出部１０１は、ＵＥ１０からＭＥＣ６０への接続要求に対し、振分装置１００からＭＥＣ６０までの通信遅延と、当該ＭＥＣ６０における処理遅延とに基づいて、振分装置１００からＭＥＣ６０までの遅延時間を算出するとともに、振分装置１００からＭＥＣ６０とは異なるＭＥＣ９０までの通信遅延と、当該ＭＥＣ９０における処理遅延とを算出し、振分装置１００からＭＥＣ９０までの遅延時間を算出する機能を有している。 The delay time calculation unit 101 determines the delay time from the distribution device 100 to the MEC60 based on the communication delay from the distribution device 100 to the MEC60 and the processing delay in the MEC60 in response to the connection request from the UE 10 to the MEC60. In addition to the calculation, it has a function of calculating the communication delay from the distribution device 100 to the MEC90 different from the MEC60 and the processing delay in the MEC90, and calculating the delay time from the distribution device 100 to the MEC90.
　経路切替部１０２は、振分装置１００からＭＥＣ６０までの遅延時間と、振分装置１００からＭＥＣ９０までの遅延時間とを比較して、遅延時間の短いコンピューティングリソースにＵＥ１０が接続されるように、振分装置１００からＭＥＣ６０，９０までの経路を切り替える機能を有している。 The route switching unit 102 compares the delay time from the distribution device 100 to the MEC60 with the delay time from the distribution device 100 to the MEC90 so that the UE 10 is connected to the computing resource having the short delay time. It has a function of switching the route from the distribution device 100 to the MECs 60 and 90.
　第２の実施形態では、第１の実施形態と同様に、ＭＥＣ６０に接続されるように予め設定されているＵＥ１０から接続要求が送信されると、振分装置１００は、予め設定された内容に基づいて、中継装置３０、中継装置４０、及びＵＰＦ５０を介して、接続要求を受信する。 In the second embodiment, as in the first embodiment, when the connection request is transmitted from the UE 10 preset to be connected to the MEC 60, the distribution device 100 has the preset contents. Based on this, the connection request is received via the relay device 30, the relay device 40, and the UPF 50.
＜第２の実施形態の処理の流れ＞
　次に、第２の実施形態に係る振分装置１００が実行する処理の流れについて説明する。 <Processing flow of the second embodiment>
Next, the flow of processing executed by the distribution device 100 according to the second embodiment will be described.
≪経路切替処理（その２）≫
　図４は、第２の実施形態に係る振分装置１００が実行する経路切替処理の流れを示すフローチャートである。 ≪Route switching process (2) ≫
FIG. 4 is a flowchart showing the flow of the route switching process executed by the distribution device 100 according to the second embodiment.
　まず、ＵＥ１０からＭＥＣ６０への接続要求が送信されると、振分装置１００は、振分装置１００からＭＥＣ６０までの遅延時間ＤＴ３（第３の通信経路の遅延時間）を算出する（ステップＳ１０１）。 First, when the connection request from the UE 10 to the MEC 60 is transmitted, the distribution device 100 calculates the delay time DT3 (delay time of the third communication path) from the distribution device 100 to the MEC 60 (step S101).
　具体的には、振分装置１００の遅延時間算出部１０１は、振分装置１００に接続されるＭＥＣ６０（第１のコンピューティングリソース）の通信遅延のΔｉと、当該ＭＥＣ６０（第１のコンピューティングリソース）における処理遅延のΔαとに基づいて、振分装置１００からＭＥＣ６０（第１のコンピューティングリソース）までの遅延時間ＤＴ３（Δｉ＋Δα）を算出する。 Specifically, the delay time calculation unit 101 of the distribution device 100 has a communication delay Δi of the MEC60 (first computing resource) connected to the distribution device 100 and the MEC60 (first computing resource). ), The delay time DT3 (Δi + Δα) from the distribution device 100 to the MEC60 (first computing resource) is calculated based on the processing delay Δα.
　次に、振分装置１００は、振分装置１００からＭＥＣ９０までの遅延時間ＤＴ４（第４の通信経路の遅延時間）を算出する（ステップＳ１０３）。 Next, the distribution device 100 calculates the delay time DT4 (delay time of the fourth communication path) from the distribution device 100 to the MEC90 (step S103).
　具体的には、振分装置１００の遅延時間算出部１０１は、振分装置１００に接続されるＵＰＦ５０の通信遅延のΔｅ、ＵＰＦ５０に接続される中継装置４０の通信遅延のΔｄ、中継装置４０に接続される中継装置７０の通信遅延のΔｆ、中継装置７０に接続されるＵＰＦ８０の通信遅延のΔｇ、ＵＰＦ８０に接続される振分装置１１０の通信遅延のΔｈ、振分装置１１０に接続されるＭＥＣ９０（第２のコンピューティングリソース）の通信遅延のΔｊ、及びＭＥＣ９０（第２のコンピューティングリソース）における処理遅延のΔβに基づいて、振分装置１００からＭＥＣ９０（第２のコンピューティングリソース）までの遅延時間ＤＴ４（Δｅ＋Δｄ＋Δｆ＋Δｇ＋Δｈ＋Δｊ＋Δβ）を算出する。 Specifically, the delay time calculation unit 101 of the distribution device 100 sets the communication delay Δe of the UPF 50 connected to the distribution device 100, the communication delay Δd of the relay device 40 connected to the UPF 50, and the relay device 40. Δf of communication delay of connected relay device 70, Δg of communication delay of UPF80 connected to relay device 70, Δh of communication delay of distribution device 110 connected to UPF80, MEC90 connected to distribution device 110 Delay from distribution device 100 to MEC90 (second computing resource) based on communication delay Δj of (second computing resource) and processing delay Δβ in MEC90 (second computing resource). The time DT4 (Δe + Δd + Δf + Δg + Δh + Δj + Δβ) is calculated.
　そして、振分装置１００は、第３の通信経路の遅延時間ＤＴ３が、第４の通信経路の遅延時間ＤＴ４以下か否かを判定し（ステップＳ１０５）、遅延時間ＤＴ３が遅延時間ＤＴ４以下の場合（ステップＳ１０５のＹｅｓ）、ＭＥＣ６０での処理は適切であると判定し、ＵＥ１０をＭＥＣ６０に接続して（ステップＳ１０７）、経路切替処理を終了する。 Then, the distribution device 100 determines whether or not the delay time DT3 of the third communication path is the delay time DT4 or less of the fourth communication path (step S105), and when the delay time DT3 is the delay time DT4 or less. (Yes in step S105), it is determined that the processing in MEC60 is appropriate, the UE 10 is connected to MEC60 (step S107), and the route switching processing is terminated.
　一方、第３の通信経路の遅延時間ＤＴ３が、第４の通信経路の遅延時間ＤＴ４より大きい場合（ステップＳ１０５のＮｏ）、ＭＥＣ６０で処理するよりもＭＥＣ９０で処理した方が、遅延時間が短いため、振分装置１００は、ＵＥ１０がＭＥＣ９０に接続されるように経路を切り替えて（ステップＳ１０９）、処理を終了する。 On the other hand, when the delay time DT3 of the third communication path is larger than the delay time DT4 of the fourth communication path (No in step S105), the delay time is shorter when processed by MEC90 than when processed by MEC60. , The distribution device 100 switches the route so that the UE 10 is connected to the MEC 90 (step S109), and ends the process.
　このように、振分装置１００の経路切替部１０２は、振分装置１００からＭＥＣ６０までの遅延時間ＤＴ３と、振分装置１００からＭＥＣ９０までの遅延時間ＤＴ４とを比較して、遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続されるように、振分装置１００からＭＥＣ６０，９０までの経路を切り替える。 As described above, the route switching unit 102 of the distribution device 100 compares the delay time DT3 from the distribution device 100 to the MEC60 with the delay time DT4 from the distribution device 100 to the MEC90, and the MEC60 has a shorter delay time. The route from the distribution device 100 to the MECs 60 and 90 is switched so that the UE 10 is connected to the and 90.
　なお、振分装置１００は、ＭＥＣ６０からＭＥＣ９０へ接続を変更する場合、接続要求メッセージ内に、接続先がＭＥＣ９０である旨を設定する。 When changing the connection from MEC60 to MEC90, the distribution device 100 sets in the connection request message that the connection destination is MEC90.
　以上説明したように、第２の実施形態によれば、第１の実施形態と同様に、振分装置１００は、最も遅延量（例えば、遅延時間）の少ないＭＥＣ６０，９０に接続するようにＭＥＣ６０，９０の経路を動的に切り替えることにより、低遅延なサービスを提供することができる。 As described above, according to the second embodiment, as in the first embodiment, the distribution device 100 is connected to the MEC60, 90 having the smallest delay amount (for example, delay time). By dynamically switching the routes of, 90, it is possible to provide a low-latency service.
＜第３の実施形態＞
　第３の実施形態では、第１の実施形態に係る中継装置４０、又は第２の実施形態に係る振分装置１００の代わりに、別途、集約装置を配置し、当該集約装置に算出部と経路決定部とを設ける。 <Third embodiment>
In the third embodiment, instead of the relay device 40 according to the first embodiment or the distribution device 100 according to the second embodiment, an aggregation device is separately arranged, and a calculation unit and a route are provided in the aggregation device. A decision unit is provided.
　この場合、集約装置は、ＵＥ１０が接続される、接続先のＭＥＣ６０，９０の経路を決定することができるので、ＵＥ１０又は基地局２０は、最初に集約装置に問合せを行うことにより、接続先のＭＥＣ６０，９０と、そのＭＥＣ６０，９０に接続される経路を取得することができる。 In this case, since the aggregation device can determine the route of the connection destination MEC60, 90 to which the UE 10 is connected, the UE 10 or the base station 20 first makes an inquiry to the aggregation device to connect to the connection destination. The MEC60,90 and the route connected to the MEC60,90 can be acquired.
　図５は、第３の実施形態に係る集約装置１２０が配置されるネットワークシステム５０２の通信経路の例を説明する図である。図５では、第１の実施形態に係る中継装置４０が配置されたネットワークシステム５００において、更に集約装置１２０が配置されたネットワークシステム５０２の構成を示している。 FIG. 5 is a diagram illustrating an example of a communication path of the network system 502 in which the aggregation device 120 according to the third embodiment is arranged. FIG. 5 shows the configuration of the network system 502 in which the aggregation device 120 is further arranged in the network system 500 in which the relay device 40 according to the first embodiment is arranged.
　なお、第１の実施形態で説明した内容と同一の構成については同一の符号を付し、適宜、説明を省略する。 Note that the same components as those described in the first embodiment are designated by the same reference numerals, and the description thereof will be omitted as appropriate.
　図５に示すように、集約装置１２０は、算出部１２１と、経路決定部１２２とを備えて構成されている。 As shown in FIG. 5, the aggregation device 120 includes a calculation unit 121 and a routing unit 122.
　算出部１２１は、中継装置４０の総遅延時間算出部４１、又は振分装置１００の遅延時間算出部１０１の機能を有している。即ち、算出部１２１は、ＵＥ１０からＭＥＣ６０への接続要求に対し、ＵＥ１０から各ＭＥＣ６０，９０までの経路ごとに総遅延時間を算出する機能か、又は、自装置である集約装置１２０から各ＭＥＣ６０，９０までの遅延時間を算出する機能を有している。 The calculation unit 121 has a function of the total delay time calculation unit 41 of the relay device 40 or the delay time calculation unit 101 of the distribution device 100. That is, the calculation unit 121 has a function of calculating the total delay time for each route from the UE 10 to each MEC60, 90 in response to a connection request from the UE 10 to the MEC60, or has a function of calculating the total delay time from the aggregation device 120, which is its own device, to each MEC60. It has a function to calculate the delay time up to 90.
　算出部１２１が、中継装置４０の総遅延時間算出部４１の機能を有する場合、経路決定部１２２は、算出された各ＭＥＣ６０，９０までの経路ごとの総遅延時間のうち、最も総遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続されるように、経路を決定する機能を有する。 When the calculation unit 121 has the function of the total delay time calculation unit 41 of the relay device 40, the route determination unit 122 has the most total delay time among the calculated total delay times for each route up to MEC60, 90. It has a function of determining a route so that the UE 10 is connected to the short MECs 60 and 90.
　また、算出部１２１が、振分装置１００の遅延時間算出部１０１の機能を有する場合、経路決定部１２２は、自装置である集約装置１２０から各ＭＥＣ６０，９０までの遅延時間を比較して、遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続されるように、経路を決定する機能を有する。 When the calculation unit 121 has the function of the delay time calculation unit 101 of the distribution device 100, the route determination unit 122 compares the delay times from the aggregation device 120, which is its own device, to the MECs 60 and 90, respectively. It has a function of determining a route so that the UE 10 is connected to the MECs 60 and 90 having a short delay time.
＜第３の実施形態の処理の流れ＞
　次に、第３の実施形態に係る集約装置１２０が実行する処理の流れについて説明する。 <Processing flow of the third embodiment>
Next, the flow of processing executed by the aggregation device 120 according to the third embodiment will be described.
　図５に示すように、集約装置１２０は、ＵＥ１０又は基地局２０から問合せ要求を受け付ける。集約装置１２０は、算出部１２１において、ＵＥ１０から各ＭＥＣ６０，９０までの経路ごとに総遅延時間を算出、又は、自装置である集約装置１２０から、各ＭＥＣ６０，９０までの遅延時間の算出を行う。 As shown in FIG. 5, the aggregation device 120 receives an inquiry request from the UE 10 or the base station 20. The aggregation device 120 calculates the total delay time for each route from the UE 10 to each MEC60, 90 in the calculation unit 121, or calculates the delay time from the aggregation device 120, which is its own device, to each MEC60, 90. ..
　経路決定部１２２は、最も総遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続される経路の決定、又は、遅延時間を比較した結果、遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続される経路の決定をすると、その経路を、ＵＥ１０又は基地局２０に回答（応答）する。 The route determination unit 122 determines the route to which the UE 10 is connected to the MECs 60 and 90 having the shortest total delay time, or determines the route to which the UE 10 is connected to the MECs 60 and 90 having the shortest delay time as a result of comparing the delay times. Then, the route is answered (response) to the UE 10 or the base station 20.
　このように、集約装置１２０は、ＵＥ１０又は集約装置１２０に低遅延なサービスを提供することができる接続先のＭＥＣ６０，９０の経路を回答（応答）することができるので、ＵＥ１０又は基地局２０は、ネットワークシステム５０２において、遅延量の少ないＭＥＣ６０，９０にＵＥ１０を接続する経路を取得することができる。 In this way, the aggregation device 120 can respond (respond) to the route of the connection destination MEC60, 90 capable of providing the UE 10 or the aggregation device 120 with a low delay service, so that the UE 10 or the base station 20 can respond. , In the network system 502, it is possible to acquire a route for connecting the UE 10 to the MECs 60 and 90 having a small delay amount.
　したがって、例えば、中継装置４０が遅延量の少ないＭＥＣ６０，９０にＵＥ１０を接続する経路を取得することにより、ＵＥ１０の接続先を切り替えることができる。 Therefore, for example, the relay device 40 can switch the connection destination of the UE 10 by acquiring a route for connecting the UE 10 to the MECs 60 and 90 having a small delay amount.
＜ハードウェア構成＞
　第１の実施形態に係る中継装置３０，４０，７０、第２の実施形態に係る振分装置１００，１１０、及び、第３の実施形態に係る集約装置１２０は、例えば、図６に示すようなコンピュータ９００によって実現される。 <Hardware configuration>
The relay devices 30, 40, 70 according to the first embodiment, the distribution devices 100, 110 according to the second embodiment, and the aggregation device 120 according to the third embodiment are, for example, as shown in FIG. It is realized by a computer 900.
　図６は、第１の実施形態に係る中継装置３０，４０，７０の機能、第２の実施形態に係る振分装置１００，１１０の機能、及び、第３の実施形態に係る集約装置１２０の機能を実現するコンピュータ９００の一例を示すハードウェア構成図である。 FIG. 6 shows the functions of the relay devices 30, 40, 70 according to the first embodiment, the functions of the distribution devices 100, 110 according to the second embodiment, and the aggregation device 120 according to the third embodiment. It is a hardware block diagram which shows an example of the computer 900 which realizes a function.
　コンピュータ９００は、ＣＰＵ（Central Processing Unit）９０１、ＲＯＭ（Read Only Memory）９０２、ＲＡＭ（Random Access Memory）９０３、ＨＤＤ（Hard Disk Drive）９０４、入出力Ｉ／Ｆ（Interface）９０５、通信Ｉ／Ｆ９０６、及びメディアＩ／Ｆ９０７を有する。 The computer 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, an HDD (Hard Disk Drive) 904, an input / output I / F (Interface) 905, and a communication I / F 906. , And media I / F907.
　ＣＰＵ９０１は、ＲＯＭ９０２またはＨＤＤ９０４に記憶されたプログラムに基づき作動し、図１に示された、中継装置４０の総遅延時間算出部４１、経路切替部４２として機能する。また、ＣＰＵ９０１は、ＲＯＭ９０２またはＨＤＤ９０４に記憶されたプログラムに基づき作動し、図３に示された、振分装置１００の遅延時間算出部１０１、経路切替部１０２として機能する。また、ＣＰＵ９０１は、ＲＯＭ９０２またはＨＤＤ９０４に記憶されたプログラムに基づき作動し、図５に示された、集約装置１２０の算出部１２１、経路決定部１２２として機能する。 The CPU 901 operates based on the program stored in the ROM 902 or the HDD 904, and functions as the total delay time calculation unit 41 and the route switching unit 42 of the relay device 40 shown in FIG. Further, the CPU 901 operates based on the program stored in the ROM 902 or the HDD 904, and functions as the delay time calculation unit 101 and the route switching unit 102 of the distribution device 100 shown in FIG. Further, the CPU 901 operates based on the program stored in the ROM 902 or the HDD 904, and functions as the calculation unit 121 and the routing unit 122 of the aggregation device 120 shown in FIG.
　ＲＯＭ９０２は、コンピュータ９００の起動時にＣＰＵ９０１により実行されるブートプログラムや、コンピュータ９００のハードウェアに係るプログラム等を記憶する。 The ROM 902 stores a boot program executed by the CPU 901 when the computer 900 is started, a program related to the hardware of the computer 900, and the like.
　ＣＰＵ９０１は、入出力Ｉ／Ｆ９０５を介して、マウスやキーボード等の入力装置９１０、および、ディスプレイ等の出力装置９１１を制御する。ＣＰＵ９０１は、入出力Ｉ／Ｆ９０５を介して、入力装置９１０からデータを取得するともに、生成したデータを出力装置９１１へ出力する。なお、プロセッサとしてＣＰＵ９０１とともに、ＧＰＵ等を用いても良い。 The CPU 901 controls an input device 910 such as a mouse and a keyboard and an output device 911 such as a display via the input / output I / F 905. The CPU 901 acquires data from the input device 910 and outputs the generated data to the output device 911 via the input / output I / F 905. A GPU or the like may be used together with the CPU 901 as the processor.
　ＨＤＤ９０４は、ＣＰＵ９０１により実行されるプログラムおよび当該プログラムによって使用されるデータ等を記憶する。通信Ｉ／Ｆ９０６は、通信網（例えば、ＮＷ（Network）９２０）を介して他の装置からデータを受信してＣＰＵ９０１へ出力し、また、ＣＰＵ９０１が生成したデータを、通信網を介して他の装置へ送信する。 The HDD 904 stores a program executed by the CPU 901, data used by the program, and the like. The communication I / F906 receives data from another device via a communication network (for example, NW (Network) 920) and outputs the data to the CPU 901, and the communication I / F 906 transfers the data generated by the CPU 901 to another device via the communication network. Send to the device.
　メディアＩ／Ｆ９０７は、記録媒体９１２に格納されたプログラムまたはデータを読み取り、ＲＡＭ９０３を介してＣＰＵ９０１へ出力する。ＣＰＵ９０１は、目的の処理に係るプログラムを、メディアＩ／Ｆ９０７を介して記録媒体９１２からＲＡＭ９０３上にロードし、ロードしたプログラムを実行する。記録媒体９１２は、ＤＶＤ（Digital Versatile Disc）、ＰＤ（Phase change rewritable Disk）等の光学記録媒体、ＭＯ（Magneto Optical disk）等の光磁気記録媒体、磁気記録媒体、導体メモリテープ媒体又は半導体メモリ等である。 The media I / F907 reads the program or data stored in the recording medium 912 and outputs the program or data to the CPU 901 via the RAM 903. The CPU 901 loads the program related to the target processing from the recording medium 912 onto the RAM 903 via the media I / F 907, and executes the loaded program. The recording medium 912 is an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto Optical disk), a magnetic recording medium, a conductor memory tape medium, a semiconductor memory, or the like. Is.
　例えば、コンピュータ９００が第１の実施形態に係る中継装置４０として機能する場合、コンピュータ９００のＣＰＵ９０１は、ＲＡＭ９０３上にロードされたプログラムを実行することにより、中継装置４０の機能（総遅延時間算出部４１、経路切替部４２）を実現する。 For example, when the computer 900 functions as the relay device 40 according to the first embodiment, the CPU 901 of the computer 900 executes the program loaded on the RAM 903 to function the relay device 40 (total delay time calculation unit). 41, the route switching unit 42) is realized.
　また、コンピュータ９００が第２の実施形態に係る振分装置１００として機能する場合、コンピュータ９００のＣＰＵ９０１は、ＲＡＭ９０３上にロードされたプログラムを実行することにより、振分装置１００の機能（遅延時間算出部１０１、経路切替部１０２）を実現する。 Further, when the computer 900 functions as the distribution device 100 according to the second embodiment, the CPU 901 of the computer 900 executes the program loaded on the RAM 903 to execute the function of the distribution device 100 (delay time calculation). Unit 101, route switching unit 102) is realized.
　また、コンピュータ９００が第３の実施形態に係る集約装置１２０として機能する場合、コンピュータ９００のＣＰＵ９０１は、ＲＡＭ９０３上にロードされたプログラムを実行することにより、集約装置１２０の機能（算出部１２１、経路決定部１２２）を実現する。 Further, when the computer 900 functions as the aggregation device 120 according to the third embodiment, the CPU 901 of the computer 900 executes the program loaded on the RAM 903 to execute the function of the aggregation device 120 (calculation unit 121, route). The determination unit 122) is realized.
　ＨＤＤ９０４には、ＲＡＭ９０３内のデータが記憶される。ＣＰＵ９０１は、目的の処理に係るプログラムを記録媒体９１２から読み取って実行する。この他、ＣＰＵ９０１は、他の装置から通信網（ＮＷ９２０）を介して目的の処理に係るプログラムを読み込んでもよい。 The data in the RAM 903 is stored in the HDD 904. The CPU 901 reads the program related to the target processing from the recording medium 912 and executes it. In addition, the CPU 901 may read a program related to the target processing from another device via the communication network (NW920).
＜効果＞
　以下、第１の実施形態に係る中継装置４０等の効果について説明する。
　本発明に係る中継装置４０は、ＵＥ１０からＭＥＣ６０への接続要求に対し、ＵＥ１０から当該ＵＥ１０と接続可能な各ＭＥＣ６０，９０までの通信遅延時間を算出するともに、各ＭＥＣ６０，９０における処理遅延時間を算出し、各ＭＥＣ６０，９０における処理遅延時間と、ＵＥ１０から各ＭＥＣ６０，９０までの通信遅延時間とに基づいて、ＵＥ１０から各ＭＥＣ６０，９０までの経路ごとに総遅延時間を算出する総遅延時間算出部４１と、算出された各ＭＥＣ６０，９０までの経路ごとの総遅延時間のうち、最も総遅延時間の短いＭＥＣにＵＥ１０が接続されるように、ＵＥ１０からＭＥＣ６０，９０に接続される経路を切り替える経路切替部４２と、を備えることを特徴とする。 <Effect>
Hereinafter, the effects of the relay device 40 and the like according to the first embodiment will be described.
The relay device 40 according to the present invention calculates the communication delay time from the UE 10 to each MEC60, 90 that can connect to the UE 10 in response to the connection request from the UE 10 to the MEC60, and also calculates the processing delay time in each MEC60, 90. Total delay time calculation to calculate and calculate the total delay time for each route from UE 10 to MEC 60, 90 based on the processing delay time in each MEC 60, 90 and the communication delay time from UE 10 to each MEC 60, 90. Of the total delay times for each route to each of the calculated MECs 60 and 90, the route connected from the UE 10 to the MECs 60 and 90 is switched so that the UE 10 is connected to the MEC having the shortest total delay time. It is characterized by including a route switching unit 42.
　これにより、ＵＥ１０からＭＥＣ６０への接続要求が送信されると、中継装置４０は、ＵＥ１０からＭＥＣ６０までの総遅延時間ＤＴ１（第１の通信経路の遅延時間）を算出するとともに、ＵＥ１０からＭＥＣ９０までの総遅延時間ＤＴ２（第２の通信経路の遅延時間）を算出する。また、中継装置４０の経路切替部４２は、算出された各ＭＥＣ６０，９０の経路ごとの総遅延時間ＤＴ１，ＤＴ２のうち、最も総遅延時間の短いＭＥＣ６０，９０の経路にＵＥ１０が接続されるように、ＵＥ１０からＭＥＣ６０，９０までの経路を切り替える。 As a result, when the connection request from the UE 10 to the MEC 60 is transmitted, the relay device 40 calculates the total delay time DT1 (delay time of the first communication path) from the UE 10 to the MEC 60, and also from the UE 10 to the MEC 90. The total delay time DT2 (delay time of the second communication path) is calculated. Further, the route switching unit 42 of the relay device 40 connects the UE 10 to the route of MEC60, 90 having the shortest total delay time among the calculated total delay times DT1 and DT2 for each MEC60,90 route. , The route from UE10 to MEC60,90 is switched.
　第１の実施形態によれば、中継装置４０は、最も遅延量の少ないＭＥＣ６０，９０にＵＥ１０を接続するようにＭＥＣ６０，９０の経路を動的に切り替えることにより、低遅延なサービスを提供することができる。 According to the first embodiment, the relay device 40 provides a low-delay service by dynamically switching the route of the MEC 60, 90 so as to connect the UE 10 to the MEC 60, 90 having the smallest delay amount. Can be done.
　次に、第２の実施形態に係る振分装置１００等の効果について説明する。
　本発明に係る振分装置１００は、ＵＥ１０からＭＥＣ６０への接続要求に対し、自装置である振分装置１００からＭＥＣ６０までの通信遅延と、当該ＭＥＣ６０における処理遅延とに基づいて、振分装置１００からＭＥＣ６０までの遅延時間を算出するとともに、振分装置１００からＭＥＣ６０とは異なるＭＥＣ９０までの通信遅延と、当該ＭＥＣ９０における処理遅延を算出し、振分装置１００からＭＥＣ９０までの遅延時間を算出する遅延時間算出部１０１と、振分装置１００からＭＥＣ６０までの遅延時間と、振分装置１００からＭＥＣ９０までの遅延時間とを比較して、遅延時間の短いＭＥＣにＵＥ１０が接続されるように、振分装置１００からＭＥＣ６０，９０までの経路を切り替える経路切替部１０２と、を備えることを特徴とする。 Next, the effect of the distribution device 100 and the like according to the second embodiment will be described.
The distribution device 100 according to the present invention responds to a connection request from the UE 10 to the MEC 60 based on a communication delay from the distribution device 100 to the MEC 60, which is its own device, and a processing delay in the MEC 60. The delay time from the distribution device 100 to the MEC60 is calculated, the communication delay from the distribution device 100 to the MEC90 different from the MEC60, and the processing delay in the MEC90 are calculated, and the delay time from the distribution device 100 to the MEC90 is calculated. The time calculation unit 101 compares the delay time from the distribution device 100 to the MEC 60 and the delay time from the distribution device 100 to the MEC 90, and distributes the UE 10 so that the UE 10 is connected to the MEC having a short delay time. It is characterized by including a route switching unit 102 for switching a route from the device 100 to the MECs 60 and 90.
　これにより、振分装置１００は、振分装置１００からＭＥＣ６０までの遅延時間ＤＴ３（第３の通信経路の遅延時間）を算出するとともに、振分装置１００からＭＥＣ９０までの遅延時間ＤＴ４（第４の通信経路の遅延時間）を算出する。また、振分装置１００の経路切替部１０２は、振分装置１００からＭＥＣ６０までの遅延時間ＤＴ３と、振分装置１００からＭＥＣ９０までの遅延時間ＤＴ４とを比較して、遅延時間の短いＭＥＣ６０，９０にＵＥ１０が接続されるように、振分装置１００からＭＥＣ６０，９０までの経路を切り替える。 As a result, the distribution device 100 calculates the delay time DT3 (delay time of the third communication path) from the distribution device 100 to the MEC60, and the delay time DT4 (fourth) from the distribution device 100 to the MEC90. (Delay time of communication path) is calculated. Further, the route switching unit 102 of the distribution device 100 compares the delay time DT3 from the distribution device 100 to the MEC60 with the delay time DT4 from the distribution device 100 to the MEC90, and the MEC60, 90 having a short delay time. The route from the distribution device 100 to the MECs 60 and 90 is switched so that the UE 10 is connected to.
　第２の実施形態によれば、振分装置１００は、最も遅延量の少ないＭＥＣ６０，９０にＵＥ１０を接続するようにＭＥＣ６０，９０の経路を動的に切り替えることにより、低遅延なサービスを提供することができる。 According to the second embodiment, the distribution device 100 provides a low-delay service by dynamically switching the route of the MEC 60, 90 so as to connect the UE 10 to the MEC 60, 90 having the smallest delay amount. be able to.
　なお、本発明は、以上説明した実施形態に限定されるものではなく、多くの変形が本発明の技術的思想内で当分野において通常の知識を有する者により可能である。 The present invention is not limited to the embodiments described above, and many modifications can be made by a person having ordinary knowledge in the art within the technical idea of the present invention.
５００，５０１,５０２　ネットワークシステム
１０　ＵＥ（通信端末）
３０，４０，７０　中継装置
６０，９０　ＭＥＣ（コンピューティングリソース）
４１　総遅延時間算出部
４２　経路切替部
１００，１１０　振分装置
１０１　遅延時間算出部
１０２　経路切替部
１２０　集約装置
１２１　算出部
１２２　経路決定部 500,501,502 Network system 10 UE (communication terminal)
30, 40, 70 Relay device 60, 90 MEC (computing resource)
41 Total delay time calculation unit 42 Route switching unit 100, 110 Distribution device 101 Delay time calculation unit 102 Route switching unit 120 Aggregation device 121 Calculation unit 122 Route determination unit

Claims (6)

  1. 　通信端末からコンピューティングリソースへの接続要求に対し、前記通信端末から当該通信端末と接続可能な各前記コンピューティングリソースまでの通信遅延時間を算出するともに、
    　各前記コンピューティングリソースにおける処理遅延時間を算出し、各当該コンピューティングリソースにおける処理遅延時間と、前記通信端末から各前記コンピューティングリソースまでの通信遅延時間とに基づいて、前記通信端末から各前記コンピューティングリソースまでの経路ごとに総遅延時間を算出する総遅延時間算出部と、
    　算出された各前記コンピューティングリソースまでの経路ごとの前記総遅延時間のうち、最も前記総遅延時間の短い前記コンピューティングリソースに前記通信端末が接続されるように、前記経路を切り替える経路切替部と、
    　を備えることを特徴とする中継装置。     In response to a connection request from a communication terminal to a computing resource, the communication delay time from the communication terminal to each computing resource that can be connected to the communication terminal is calculated, and the communication delay time is calculated.
    The processing delay time in each of the computing resources is calculated, and based on the processing delay time in each of the computing resources and the communication delay time from the communication terminal to each of the computing resources, each of the computing from the communication terminal. A total delay time calculation unit that calculates the total delay time for each route to the ing resource,
    A route switching unit that switches the route so that the communication terminal is connected to the computing resource having the shortest total delay time among the calculated total delay times for each route to the computing resource. ,
    A relay device characterized by being provided with.
  2. 　通信端末から第１のコンピューティングリソースへの接続要求に対し、自装置である振分装置から前記第１のコンピューティングリソースまでの通信遅延と、当該第１のコンピューティングリソースにおける処理遅延とに基づいて、前記自装置から前記第１のコンピューティングリソースまでの遅延時間を算出するとともに、
    　前記自装置から前記第１のコンピューティングリソースとは異なる第２のコンピューティングリソースまでの通信遅延と、当該第２のコンピューティングリソースにおける処理遅延とを算出し、前記自装置から前記第２のコンピューティングリソースまでの遅延時間を算出する遅延時間算出部と、
    　前記自装置から前記第１のコンピューティングリソースまでの遅延時間と、前記自装置から前記第２のコンピューティングリソースまでの遅延時間とを比較して、遅延時間の短いコンピューティングリソースに前記通信端末が接続されるように、前記自装置から前記第１又は第２のコンピューティングリソースまでの経路を切り替える経路切替部と、
    　を備えることを特徴とする振分装置。     Based on the communication delay from the distribution device, which is the own device, to the first computing resource, and the processing delay in the first computing resource in response to the connection request from the communication terminal to the first computing resource. Then, while calculating the delay time from the own device to the first computing resource,
    The communication delay from the own device to the second computing resource different from the first computing resource and the processing delay in the second computing resource are calculated, and the second computing from the own device is calculated. A delay time calculation unit that calculates the delay time to the ing resource,
    Comparing the delay time from the own device to the first computing resource and the delay time from the own device to the second computing resource, the communication terminal is assigned to the computing resource having a short delay time. A route switching unit that switches the route from the own device to the first or second computing resource so as to be connected.
    A sorting device characterized by being equipped with.
  3. 　中継装置の経路切替方法であって、
    　前記中継装置は、
    　通信端末からコンピューティングリソースへの接続要求に対し、前記通信端末から当該通信端末と接続可能な各前記コンピューティングリソースまでの通信遅延時間を算出するとともに、
    　各前記コンピューティングリソースにおける処理遅延時間を算出し、各当該コンピューティングリソースにおける処理遅延時間と、前記通信端末から各前記コンピューティングリソースまでの通信遅延時間とに基づいて、前記通信端末から各前記コンピューティングリソースまでの経路ごとに総遅延時間を算出するステップと、
    　算出された各前記コンピューティングリソースまでの経路ごとの前記総遅延時間のうち、最も前記総遅延時間の短い前記コンピューティングリソースに前記通信端末が接続されるように、前記経路を切り替えるステップと、
    　を実行することを特徴とする経路切替方法。     It is a method of switching the route of the relay device.
    The relay device is
    In response to a connection request from a communication terminal to a computing resource, the communication delay time from the communication terminal to each of the computing resources connectable to the communication terminal is calculated, and the communication delay time is calculated.
    The processing delay time in each of the computing resources is calculated, and based on the processing delay time in each of the computing resources and the communication delay time from the communication terminal to each of the computing resources, each of the computing from the communication terminal. A step to calculate the total delay time for each route to the ing resource,
    A step of switching the route so that the communication terminal is connected to the computing resource having the shortest total delay time among the calculated total delay times for each route to the computing resource.
    A route switching method characterized by executing.
  4. 　振分装置の経路切替方法であって、
    　前記振分装置は、
    　通信端末から第１のコンピューティングリソースへの接続要求に対し、自装置である振分装置から前記第１のコンピューティングリソースまでの通信遅延と、当該第１のコンピューティングリソースにおける処理遅延とに基づいて、前記自装置から前記第１のコンピューティングリソースまでの遅延時間を算出するとともに、
    　前記自装置から前記第１のコンピューティングリソースとは異なる第２のコンピューティングリソースまでの通信遅延と、当該第２のコンピューティングリソースにおける処理遅延時間とを算出し、前記自装置から前記第２のコンピューティングリソースまでの遅延時間を算出するステップと、
    　前記自装置から前記第１のコンピューティングリソースまでの遅延時間と、前記自装置から前記第２のコンピューティングリソースまでの遅延時間とを比較して、遅延時間の短いコンピューティングリソースに前記通信端末が接続されるように、前記自装置から前記第１又は第２のコンピューティングリソースまでの経路を切り替えるステップと、
    　を実行することを特徴とする振分装置の経路切替方法。     It is a method of switching the route of the distribution device.
    The sorting device is
    Based on the communication delay from the distribution device, which is the own device, to the first computing resource, and the processing delay in the first computing resource in response to the connection request from the communication terminal to the first computing resource. Then, while calculating the delay time from the own device to the first computing resource,
    The communication delay from the own device to the second computing resource different from the first computing resource and the processing delay time in the second computing resource are calculated, and the second one is calculated from the own device. Steps to calculate the delay time to the computing resource,
    Comparing the delay time from the own device to the first computing resource and the delay time from the own device to the second computing resource, the communication terminal is assigned to the computing resource having a short delay time. A step of switching the route from the own device to the first or second computing resource so as to be connected.
    A method of switching routes of a sorting device, which comprises executing.
  5. 　コンピュータに、
    　通信端末からコンピューティングリソースへの接続要求に対し、前記通信端末から当該通信端末と接続可能な各前記コンピューティングリソースまでの通信遅延時間を算出させるとともに、
    　各前記コンピューティングリソースにおける処理遅延時間を算出し、各当該コンピューティングリソースにおける処理遅延時間と、前記通信端末から各前記コンピューティングリソースまでの通信遅延時間とに基づいて、前記通信端末から各前記コンピューティングリソースまでの経路ごとに総遅延時間を算出させる手順、
    　算出された各前記コンピューティングリソースまでの経路ごとの前記総遅延時間のうち、最も前記総遅延時間の短い前記コンピューティングリソースに前記通信端末が接続されるように、前記経路を切り替えさせる手順、
    　を実行させるためのプログラム。     On the computer
    In response to a connection request from a communication terminal to a computing resource, the communication delay time from the communication terminal to each computing resource that can connect to the communication terminal is calculated, and at the same time, the communication delay time is calculated.
    The processing delay time in each of the computing resources is calculated, and based on the processing delay time in each of the computing resources and the communication delay time from the communication terminal to each of the computing resources, each of the computing from the communication terminal. Procedure to calculate the total delay time for each route to the ing resource,
    A procedure for switching the route so that the communication terminal is connected to the computing resource having the shortest total delay time among the calculated total delay times for each route to the computing resource.
    A program to execute.
  6. 　コンピュータに、
    　通信端末から第１のコンピューティングリソースへの接続要求に対し、自装置である振分装置から前記第１のコンピューティングリソースまでの通信遅延と、当該第１のコンピューティングリソースにおける処理遅延とに基づいて、前記自装置から前記第１のコンピューティングリソースまでの遅延時間を算出させるとともに、
    　前記自装置から前記第１のコンピューティングリソースとは異なる第２のコンピューティングリソースまでの通信遅延と、当該第２のコンピューティングリソースにおける処理遅延時間を算出し、前記自装置から前記第２のコンピューティングリソースまでの遅延時間を算出させる手順、
    　前記自装置から前記第１のコンピューティングリソースまでの遅延時間と、前記自装置から前記第２のコンピューティングリソースまでの遅延時間とを比較して、遅延時間の短いコンピューティングリソースに前記通信端末が接続されるように、前記自装置から前記第１又は第２のコンピューティングリソースまでの経路を切り替えさせる手順、
    　を実行させるためのプログラム。     On the computer
    Based on the communication delay from the distribution device, which is the own device, to the first computing resource, and the processing delay in the first computing resource in response to the connection request from the communication terminal to the first computing resource. Then, the delay time from the own device to the first computing resource is calculated, and the delay time is calculated.
    The communication delay from the own device to the second computing resource different from the first computing resource and the processing delay time in the second computing resource are calculated, and the second computing from the own device is calculated. Procedure for calculating the delay time to the ing resource,
    Comparing the delay time from the own device to the first computing resource and the delay time from the own device to the second computing resource, the communication terminal is assigned to the computing resource having a short delay time. A procedure for switching the route from the own device to the first or second computing resource so as to be connected.
    A program to execute.
PCT/JP2020/027200 2020-07-13 2020-07-13 Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program WO2022013907A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022535987A JP7435783B2 (en) 2020-07-13 2020-07-13 Relay device, distribution device, route switching method for relay device, route switching method for distribution device, and program
PCT/JP2020/027200 WO2022013907A1 (en) 2020-07-13 2020-07-13 Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/027200 WO2022013907A1 (en) 2020-07-13 2020-07-13 Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program

Publications (1)

Publication Number Publication Date
WO2022013907A1 true WO2022013907A1 (en) 2022-01-20

Family

ID=79555226

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/027200 WO2022013907A1 (en) 2020-07-13 2020-07-13 Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program

Country Status (2)

Country Link
JP (1) JP7435783B2 (en)
WO (1) WO2022013907A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006332825A (en) * 2005-05-24 2006-12-07 Fujitsu Ltd Program, method, and device for dispersing load
JP2012209660A (en) * 2011-03-29 2012-10-25 Kddi Corp Path setting method considering effect of data compression in network
JP2018088041A (en) * 2016-11-28 2018-06-07 富士通株式会社 Connection number control program, distribution apparatus and connection number control method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10624021B2 (en) 2015-08-20 2020-04-14 Nec Corporation Communication system, base station device, control device, and communication method
JP7137208B2 (en) 2018-11-13 2022-09-14 株式会社国際電気通信基礎技術研究所 COMMUNICATION METHOD, PROGRAM, COMMUNICATION TERMINAL, AND MEC SERVER

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006332825A (en) * 2005-05-24 2006-12-07 Fujitsu Ltd Program, method, and device for dispersing load
JP2012209660A (en) * 2011-03-29 2012-10-25 Kddi Corp Path setting method considering effect of data compression in network
JP2018088041A (en) * 2016-11-28 2018-06-07 富士通株式会社 Connection number control program, distribution apparatus and connection number control method

Also Published As

Publication number Publication date
JP7435783B2 (en) 2024-02-21
JPWO2022013907A1 (en) 2022-01-20

Similar Documents

Publication Publication Date Title
WO2020135800A1 (en) Domain name server allocation method and device
CN109548082B (en) Service redirection method and device
US10819636B1 (en) Methods, systems, and computer readable media for producer network function (NF) service instance wide egress rate limiting at service communication proxy (SCP)
US11064388B2 (en) Traffic distribution method through multi-access network in a network and network entity performing the same
US11178717B2 (en) Traffic distribution method through multi-access network in a network and network entity performing the same
Lu et al. Adaptive service in mobile computing environments
US11924922B2 (en) Application mobility mechanism for edge computing
Balasubramanian et al. A mobility management architecture for seamless delivery of 5G-IoT services
CN110650504A (en) Session processing method and device
WO2022007899A1 (en) Upf selection method and apparatus
JP2023500931A (en) Policy-based Access and Mobility Management Function (AMF) selection using Network Slice Selection Assistance Information (NSSAI) availability information
WO2021023018A1 (en) Service scheduling method and apparatus
Sood et al. The controller placement problem or the controller selection problem?
US20170208506A1 (en) Mobile communication system, local access server and network controller
JP2019506809A (en) Virtual network function to cooperate
WO2023155669A1 (en) Method and device for selecting user plane function
US20240163178A1 (en) Edge computing topology information exposure
Tashtarian et al. S2VC: An SDN-based framework for maximizing QoE in SVC-based HTTP adaptive streaming
CN111699659B (en) Virtualized network functions
Anbalagan et al. SDN-assisted learning approach for data offloading in 5G HetNets
CN111615128A (en) Multi-access edge computing method, platform and system
WO2022013907A1 (en) Relay device, distribution device, path switching method for relay device, path switching method for distribution device, and program
Shuai et al. A cost-based distributed algorithm for load balancing in content delivery network
JP2012074825A (en) Qos guaranteed network system, centralized controller, and control method of centralized controller
Derakhshan et al. Enabling cloud connectivity using SDN and NFV technologies

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022535987

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20945682

Country of ref document: EP

Kind code of ref document: A1