JP2010224822A - Request reception method and system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a request reception method and a system to control access timing to an end server from each user terminal based on a service processing rate of the end server. <P>SOLUTION: A receiving part 31 of a correction server HS receives a service request and a service response. A transmission part 32 transmits the service request and the service response. A service start detection part 33 detects the start timing of a service based on the received service request. A service end detection part 34 detects the end timing of the service based on the received service response. An actual volume processing rate measurement part 36 measures an actual volume processing rate Creal of each end server ESj based on the elapsed time since start till end of the service. A service time calculation part 37 calculates a service time TAT of each end server ESj based on the actual volume processing rate Creal. A service time notification part 38 notifies the service time TAT to an access path server APS. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a request receiving method and system for receiving an access path request transmitted from a user terminal in advance, determining an access timing from each user terminal to an end server, and returning this as an access path to each user terminal.

  Request messages triggered by specific events, such as requests to confirm safety in the event of a disaster or requests to distribute popular songs immediately after releasing a hit chart on a TV program or radio program, are concentrated in a short time Tend. When the number of requests exceeds the processing capacity, the end server that accepts requests at these destinations cannot provide services for the excess. This lowers the satisfaction level of the user who uses the service, and if the request is distribution of paid content, the content provider loses a sales opportunity.

  Concentration of access triggered by an event far exceeds the normal access amount and may reach 10 to 100 times instantaneously. Therefore, if the server capacity is designed in accordance with the peak time when the access is concentrated, a large excess of equipment is incurred during normal times, which occupies most of the time. Moreover, since such access concentration is difficult to predict, even if equipment that is predicted to be sufficient can be prepared, the possibility of concentration of access exceeding that capacity cannot be denied.

  On the other hand, digital terrestrial broadcasting started in December 2003 in Tokyo, Osaka, and Nagoya. After that, broadcasting started in other areas and services for mobile receivers will be expanded. Yes. In the communication / broadcasting cooperation service provided by terrestrial digital broadcasting, the occurrence of simultaneous large-scale access is anticipated triggered by the contents of the program, and it is assumed that the above-mentioned phenomenon will become more apparent in the future.

  Patent Document 1 discloses a system that can accept and process re-access of a request message that has been rejected due to access concentration fairly without causing new access concentration.

  Here, when a large number of accesses are concentrated on an end server that provides a service, a message indicating that it is currently crowded and a time zone during which priority connection is made next time are presented to unacceptable users. When the same user accesses the priority connection time zone again, this request message is accepted with priority over other request messages.

  However, in Patent Document 1, when one user transmits a request message, if the load on the reception side is large, the reception is postponed, and immediately after that, when another user transmits a request message, the reception side Since the request message of the other user is received first when the load of the user is eliminated, there is a technical problem that the reception is not performed fairly.

  In order to deal with such technical problems, the inventors of the present invention, in Patent Document 2 and Non-Patent Document 1, have issued an access path request transmitted in advance from a user terminal, separately from an end server that provides services to the user. By providing an access server that receives and determines the access timing from each user terminal to the end server and returns this as an access path to each user terminal, it accepts access from the user terminals fairly and without reverse order. We propose a method and system for accepting requests.

JP 2007-219650 A JP 2009-43069 A

“Proposal of access control system using numbered ticket issuing function”, Science Technique vol.1 108 No.218, p81-p86.

  In order for the end server to process the access of the service request from the user terminal without delay, the period of the service request input to the end server and the time required for the end server to process one service request, that is, the service time ( (Turn Around Time) is desirable. Therefore, in the techniques disclosed in Patent Document 2 and Non-Patent Document 1 described above, the service time of each end server is statistically estimated in advance, and the service request is processed by each end server according to this estimated value. The access timing of each user terminal was determined.

  However, for example, in a service in which an end server distributes content such as moving images to a user terminal in response to a content distribution service request, the service time of the end server depends on the content download speed at the user terminal. And since the download speed of the user terminal depends on the capacity of the access line and the connection method (wired LAN or wired LAN, etc.), the service time of the end server is not always constant even if the provided service is the same. .

  Therefore, in the above prior art, there may be a discrepancy between the estimated value and the actual value regarding the service time of the end server, and if this becomes large, if the estimated value <the actual value, the end server will be congested and vice versa If the estimated value> the actual value, the operation efficiency of the end server is lowered.

  SUMMARY OF THE INVENTION An object of the present invention is to solve the above-described problems of the prior art, and a request reception method capable of appropriately controlling the access timing from each user terminal to the end server based on the actual service time (actual processing rate) of the end server, and To provide a system.

  In order to achieve the above object, the present invention accepts an access path request transmitted from a user terminal, determines an access timing to an end server that is permitted to each user terminal, and accesses this to each user terminal. In the request acceptance system that returns as a path, an access path server that accepts an access path request received from the user terminal and returns an access path response, receives a service request from the user terminal, forwards it to the end server, and provides it from the end server And a correction server that receives the service to be transferred to the user terminal, and the correction server has the following configuration.

  (1) Means for detecting the start timing and end timing of the service provided by the end server in response to the service request, means for calculating the service time based on each detected timing, and the service time to the access path server And the access path server determines the access timing to the end server permitted to each user terminal using the notified service time as a parameter.

  (2) The service time calculating means measures the elapsed time from the start timing to the end timing of the service a plurality of times, and uses the moving average as the service time.

  (3) The means for calculating the service time is characterized in that a standard deviation of the elapsed time is obtained and an elapsed time exceeding a predetermined range based on the standard deviation is excluded.

  According to the present invention, the following effects are achieved.

  (1) The service time of the end server is monitored, and the access timing to the end server permitted to each user terminal is determined based on the monitoring result, so that the service requests are concentrated on the end server, causing congestion. Alternatively, it is possible to determine the optimum access timing for each user terminal without reducing the service efficiency of the end server due to excessive regulation of service requests.

  (2) Since the service time is obtained as a moving average value, the influence of some specific service time can be mitigated.

  (3) Since the service time exceeding the standard time is excluded in advance, the influence of some specific service time can be eliminated.

It is a block diagram of a network to which the request reception system of the present invention is applied. It is the functional block diagram which showed the structure of the principal part of an access path server. It is the functional block diagram which showed the structure of the principal part of a correction | amendment server. It is the flowchart which showed the procedure of the request process in a user terminal. It is the flowchart which showed the procedure of the access path response process in an access path server. It is the flowchart which showed the procedure of the access timing determination process. It is the flowchart which showed the procedure which calculates the estimated probability that a user terminal transmits a service request based on the access rate of a service request. It is the flowchart which showed the procedure which calculates the estimated probability that a user terminal transmits a service request based on the access volume of an access path request. It is the figure which showed the example of a display of a reception completion message. It is the figure which showed the example of a display of a download completion message. It is the flowchart which showed the procedure of the processing rate review process in which the correction server dynamically reviews and updates the processing rate of each end server. FIG. 6 is a diagram schematically representing a method for estimating a service start time and a service end time based on a SYN / FIN packet. It is the figure which expressed typically the method of estimating the performance process rate Creal based on HTTP METHOD. It is the figure which expressed typically the method of estimating the results processing rate Creal based on the HTTP message body. It is the figure which showed a mode that the performance processing rate Creal of an end server showed Pareto distribution.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a block diagram showing the configuration of a network to which the request reception system of the present invention is applied. Here, a case where a content distribution service is requested from a user terminal MN to an end server ES (service providing server) is shown. An example will be described.

  A user terminal MN such as a mobile phone, PDA or computer is connected to an IP network NW such as a mobile phone network or the Internet via a base station AP. In addition, in response to a service request from the user terminal MN, a plurality of end servers ESj (j is an end server identifier) that distributes content such as music and video, together with an access path server APS and a correction server HS described in detail later. It is connected to the IP network NW.

  The access path server APS has a function of determining a timing for permitting each user terminal MN to access (service request) to the end server ESj and notifying each user terminal MN, and from the user terminal MN to an access end server When an access path request message including ESj identification information and content identification information is received, the access timing is determined based on the capability and status of each end server ESj, and this is notified to the requesting user terminal MN. The user terminal MN waits for the notified access timing, transmits a service request to the end server ESj, and receives a service such as content distribution from the end server ESj.

  The correction server HS operates as a reverse proxy server or a NAT (Network address Translation) box, relays a service request transmitted from the user terminal MN to the end server ESj, and is transmitted from the end server ESj to the user terminal MN. The service response is relayed, the service time TAT (Turn Around Time) in each end server ESj is measured based on the relayed service request and the transmission / reception timing of the service response, and this is notified to the access path server APS. The access path server APS updates the virtual processing rate Cj for imitating the service processing status on each end server ESj on the access path server APS based on the service time TAT.

  FIG. 2 is a functional block diagram showing the configuration of the main part of the access path server APS. Here, the configuration unnecessary for the description of the present invention is omitted. Since the response processing executed every time the access path server APS receives an access path request from each user terminal MN has a low load, the access path server APS All access path requests can be accepted without delay in the order received.

  The access path request receiving unit 11 receives an access path request transmitted from each user terminal MN. The server processing management unit 12 virtually manages the processing status of service requests in each end server ESj using queue values. The access timing determination unit 13 includes a processing rate management unit 131 that manages the time required for each end server ESj to process one service request received from the user terminal MN as the processing rate Cj. Then, as will be described later in detail, the queue server value of each end server ESj managed by the server process management unit 12 and the processing rate Cj of each end server ESj are used as parameters to simulate the service processing status of the end server ESj, The access timing to each end server ESj permitted for each user terminal MN is determined for each access path request.

  The access path response generation unit 14 generates an access path response including the access timing to the end server ESj. The access path response reply unit 15 returns the access path response to the transmission source of the access path request. The service time receiving unit 16 receives the service time TAT of each end server ESj measured by the correction server HS. The processing rate update unit 17 updates the processing rate Cj based on the received service time TAT.

  FIG. 3 is a functional block diagram showing the configuration of the main part of the correction server HS. Here, the configuration unnecessary for the description of the present invention is omitted.

  The receiving unit 31 includes a service request receiving unit 31a and a service response receiving unit 31b, and receives a service request transmitted from the user terminal MN and a service response transmitted from the end server ESj via the I / F. The transmission unit 32 includes a service request transmission unit 32a and a service response transmission unit 32b, and transmits a service request to be transferred to the end server ESj and a service response to be transferred to the user terminal MN via the I / F.

  The service start detection unit 33 detects the service start timing based on the received service request packet. The service end detection unit 34 detects the service end timing based on the received service response packet. The actual processing rate measuring unit 35 includes a timer 35 that measures the current time t0, and measures the actual processing rate Creal of each end server ESj based on the elapsed time from the service start timing to the service end timing for the same session.

  The service time calculation unit 37 calculates the service time TAT of each end server ESj based on the exponential moving average of the actual processing rate Creal. The service time notification unit 38 notifies the service time TAT of each end server ESj calculated by the service time calculation unit 37 to the access path server APS.

  Next, the operation of this embodiment will be described in detail with reference to a flowchart. FIG. 4 is a flowchart showing a procedure of request processing in the user terminal MN that requests content distribution, and FIGS. 5, 6, 7, and 8 are flowcharts showing operations of the access path server APS.

  The user operates the key switch or the like of the user terminal MN to execute a content request operation, and when this is detected in step S11 of FIG. 4, the process proceeds to step S12. In step S12, an access path request including the identifier of the requested content and the identifier of the end server ESj that provides the content is generated and transmitted to the access path server APS, and transmitted in step S13.

  Proceeding to FIG. 5, when the access path server APS receives the access path request in step S31, in step S32, the access timing determination unit 13 determines when the user terminal MN is permitted to access the end server ESj. It is determined by the following procedure.

  FIG. 6 is a flowchart showing the procedure of the access timing determination process, and mainly shows the operation of the access timing determination unit 13. In addition, the definition of each code | symbol is as follows.

i: Access path request identifier
j: End server ES identifier
ti, j: i-th access request time for the end server ESj
di, j: Standby time until the access timing assigned to the i-th access request for the end server ESj
Cj: Processing rate of each end server ESj
Qmax_j: Maximum queue value for each end server ESj
bi, j: Weight value δ: Assumed transmission delay time of access path request from access path server APS to user terminal MN
Qj (ti, j) ^- : Queue value of end server ESj immediately before receiving access path request at time ti
Qj (ti, j) ⁺ : Queue value of the end server ESj immediately after receiving the access path request at time ti
pj: Estimated probability that the user terminal MN that sent the access path request to the end server ESj will send the service request to the end server ESj at the permitted access timing

In step S321 in FIG. 6, for the end server ESj corresponding to the identifier registered in the received access path request, the queue value [Qj (ti−) immediately after receiving the previous access path request at time [ti−1]. 1, j) ⁺ ] is fetched from the server processing management unit 12. In this embodiment, one queue represents one service request.

In step S322, the processing rate Cj of the end server ESj is captured. The processing rate Cj is dynamically reviewed based on the service time TAT notified from the correction server HS, as will be described in detail later. In step S323, the unprocessed request amount of the end server ESj immediately before receiving the access path request addressed to the end server ESj at time [ti, j], that is, the queue value [Qj (ti, j) ⁻ ] Calculated in 1).

In step S324, the queue value [Qj (ti, j) ⁺ ] immediately after receiving the access path request at time [ti, j] is obtained by the following equation (2).

  Here, the weight value [bi, j] depends on the processing load of the end server ESj that processes the service request. For example, if the access path request is a distribution request for music content, the larger the size of the requested music file is, A large weight value bi, j is assigned. If weighting is not necessary, a predetermined constant (eg, “1”) is assigned to the weight value [bi, j].

In step S325, the access timing to be notified to the user terminal MN that transmitted the access path request is the waiting time [di, j] based on the reception time [ti, j] of the access path request according to the following equation (3). Desired. In step S326, the calculation result of the queue value [Qj (ti, j) ⁺ ] is updated and registered in the server processing management unit 12.

  Even when the user terminal MN receives the access path response, there may be a case where the service request cannot be transmitted at the permitted access timing due to a change in the line status or the like. In the following equation (4), in consideration of such a situation, the user terminal MN that has transmitted the service request statistically obtains the estimated probability pj (ti, j) for transmitting the service request for each end server ESj. And reflected in the waiting time [di, j].

  FIG. 7 is a flowchart showing a procedure for calculating the estimated probability Pj (ti, j) based on the access rate to the end server ESj.

  When an access path request related to the end server ESj is received in step S71, in step S72, an elapsed period from the previous access path request reception time ti-1, j to the current access path request reception time ti, j. Δti, j and the number of accesses ni, j to the end server ESj at the elapsed time Δti, j, that is, the total number of service requests are calculated.

In step S73, it is determined whether or not the queue value [Qj (ti, j) ⁻ ] of the end server ESj immediately before receiving the current access path request is greater than zero. If the queue value [Qj (ti, j) ⁻ ] is greater than zero, the process proceeds to step S74, and the cumulative access number M and elapsed time T since the queue value [Qj (ti, j) ⁻ ] has finally become zero. Is calculated. In step S75, the average access rate ARj (ti, j) to the end server ESj is calculated based on the cumulative access number M and the elapsed time T. In step S76, the estimated probability Pj (ti, j) is set based on the following equation (5). Note that the symbol Pmin is a constant of 0 <Pmin <1.

On the other hand, when the queue value [Qj (ti, j) ⁻ ] is determined to be zero in step S73, “1” is registered in the estimated probability Pj (ti, j) in step S77. In step S78, the cumulative access number M and the elapsed time T are reset.

  FIG. 8 is a flowchart showing a procedure for calculating the estimated probability Pj (ti, j) based on a service request and a content volume (hereinafter collectively referred to as an access volume).

  When an access path request related to the end server ESj is received in step S81, in step S82, an elapsed period from the previous access path request reception time ti-1, j to the current access path request reception time ti, j. The access volume vi, j of the end server ESj at Δti, j and the elapsed time Δti, j is calculated.

In step S83, it is determined whether or not the queue value [Qj (ti, j) ⁻ ] of the end server ESj immediately before receiving the current access path request is greater than zero. If the queue value [Qj (ti, j) ⁻ ] is greater than zero, the process proceeds to step S84, and the cumulative access volume W and elapsed time T since the queue value [Qj (ti, j) ⁻ ] has finally become zero. Is calculated. In step S85, the average access volume VRj (ti, j) to the end server ESj is calculated based on the cumulative access volume W and the elapsed time T. In step S86, the estimated probability Pj (ti, j) is set based on the following equation (6). Note that the symbol Pmin is a constant of 0 <Pmin <1.

On the other hand, when the queue value [Qj (ti, j) ⁻ ] is determined to be zero in step S83, “1” is registered in the estimated probability Pj (ti, j) in step S87. In step S88, the cumulative access volume W and elapsed time T are reset.

  Returning to FIG. 5, in step S33, an access path response including the waiting time [di, j] as the access timing is generated by the access path response generator 14. In step S34, the access path response is returned from the access path response return unit 15. A reply is made to the user terminal MN that sent the access path request.

  Returning to FIG. 4, when the access path response is received in step S14, the user terminal MN extracts a standby time [di, j] as an access timing registered in the access path response in step S15. The In step S16, the extracted waiting time [di, j] is compared with a predetermined upper limit value dmax. If the waiting time [di, j]> dmax, the process proceeds to step S17, and an error message indicating that the service cannot be provided is displayed. Display on the terminal display and stop the process. On the other hand, if the waiting time [di, j] ≦ dmax, the process proceeds to step S18 to indicate that the request is processed in the first-come-first-served basis as shown in FIGS. 9 (a) and 9 (b). A reception completion message is displayed on the terminal display.

  In step S19, a content request including the identifier of the content requesting distribution and the identifier of the end server is generated as a service request. In step S20, it is determined whether or not it is the access timing based on whether or not the elapsed time since the transmission of the access request path in step S13 has reached the standby time [di, j]. The process proceeds to step S21. In step S21, the service request generated in step S19 (here, a content distribution request) is transmitted with the end server ESj as the destination. Such standby processing up to the access timing in the user terminal MN can be implemented by using various script languages such as Java (registered trademark) script and Flash functions.

  The end server ESj that has received this service request prepares the requested content and distributes it to the user terminal MN.

  When receiving the content in step S22, the user terminal MN proceeds to step S23 and stores the content. In step S24, a download completion message shown as an example in FIG. 10 is displayed on the terminal display.

  FIG. 11 is a flowchart showing a processing rate review process in which the correction server HS dynamically reviews and updates the processing rate Cj of each end server ESj.

  In the correction server HS, when the service request is received by the service request receiving unit 31a in step S51, the process proceeds to step S52, and the identifier k for identifying the service request is incremented for each end server ESj. In step S53, the time required for the end server ESj to process the service request is measured by the actual processing rate measuring unit 36 to obtain the actual processing rate Creal.

  12, 13, and 14 are diagrams schematically showing a procedure for measuring the actual processing rate. When a service request and a service response are performed using a TCP session, a SYN / FIN packet, an HTTP METHOD, and an HTTP message are shown. The actual processing rate Creal is measured by monitoring the body or HTTP / 1.1 range request.

  FIG. 12 is a diagram schematically representing a method for estimating the service start time and the service end time based on the monitoring result of the SYN / FIN packet.

  The TCP session is composed of a plurality (N) of TCP connections, and each TCP connection returns a SYN-ACK to the SYN packet transmitted from the user terminal MN, and further from the user terminal MN (S). It is established by transmitting an ACK packet to the end server ESj. Then, the TCP connection established in this way is disconnected when both the user terminal MN and the end server ESj exchange FIN-ACK.

  Therefore, in the present embodiment, the time at which the first SYN-ACK transmitted from the end server ESj is received by the correction server HS is detected by the service start detection unit 33 as the service start time, and further, the Nth FIN-ACK The time when the correction server HS receives the FIN-ACK transmitted from the user terminal MN in the ACK exchange is detected as the service end time by the service end detection unit 34, and the actual processing rate measurement unit 35 starts the service start The service time from the time to the service end time is the actual processing rate Creal.

  Since the number of TCP connections (N) depends on the service content, it is desirable that the correction server HS obtains the number of TCP connections (N) for each service from each end server ES in advance.

  Whether each TCP connection is related to the same TCP session can be determined based on, for example, whether the source IP address and port number are the same, and the destination IP address and port number are the same. . Alternatively, the determination may be made based on whether the IDs unique to the transmission source terminal are the same and the destination IP address and the port number are the same.

  FIG. 13 is a diagram schematically representing a method for estimating the performance processing rate Creal based on the monitoring result of the HTTP METHOD.

  In this embodiment, a TCP connection is established between the user terminal MN and the end server ESj when an HTTP METHOD (for example, GET, POST, etc.) transmitted from the user terminal MN passes the correction server HS. This time is determined as the service start time. Furthermore, the service end time is the time when the FIN-ACK transmitted from the user terminal MN (S) in the Nth FIN-ACK exchange is received by the correction server HS, and the actual processing rate is from the service start time to the service end time. Creal.

  FIG. 14 is a diagram schematically representing a method of estimating the performance processing rate Creal based on the monitoring result of the HTTP message body.

  In the present embodiment, the HTTP message body transmitted from the user terminal MN is monitored by the correction server HS, and an identification code (for example, a character string such as “start”) indicating session start is registered in a predetermined area of the message body. When it is detected that the service has been performed, the time is set as the service start time. Further, when it is detected that an identification code (for example, a character string such as “finish”) indicating the end of the session is registered in a predetermined area of the HTTP message body transmitted from the user terminal MN, the time is The service start time is assumed. The service processing time Creal is from the service start time to the service end time.

  Returning to FIG. 11, in step S54, the service time calculation unit 37 determines that the current service time TAT [k] is an exponential smoothed moving average (TAT) of the current actual processing rate Creal and the past actual processing rate Creal. [k-1]) is calculated by the following equation (7). Here, α is a smoothing coefficient. If a moving average for m times including this time is calculated, the smoothing coefficient α is expressed by the following equation (8).

  Since the service time TAT is known to show a Pareto distribution as shown in FIG. 15, for example, the actual processing rate Creal of about 0.13% higher than three times the standard deviation (3σ) It is desirable to exclude the service time TAT from the calculation target.

  In step S55, the service time TAT [i] is temporarily stored. In step S56, the service time TAT [i] is notified to the access path server APS.

  In the access path server APS, the service time TAT [i] is received by the service time receiving unit 16 and the current processing rate Cj managed by the processing rate management unit 131 is notified by the processing rate update unit 17. Updated to the latest service time TAT [i].

  In the above embodiment, an example is given in which the user terminal acquires an access path for content distribution in advance, and transmits a content request to the end server ESj at the access timing permitted by this access path to download the content. However, the present invention is not limited to this, and the user terminal acquires in advance an access path for uploading data and content to the end server ESj, and executes the upload at the permitted access timing. The same applies to the case.

DESCRIPTION OF SYMBOLS 11 ... Access path request | requirement part, 12 ... Server process management part, 13 ... Access timing determination part, 14 ... Access path response production | generation part, 15 ... Access path response reply part, 16 ... Service time reception part, 17 ... Processing rate update , 131... Processing rate management unit, 31... Reception unit, 32... Transmission unit, 33... Service start detection unit, 34. ... Service time calculation unit, 38 ... Service time notification unit

Claims (4)

In the request reception system that accepts the access path request transmitted from the user terminal, determines the access timing to the end server permitted to each user terminal, and returns this as the access path to each user terminal.
An access path server that accepts an access path request received from the user terminal and returns an access path response; and
A correction server for receiving a service request from a user terminal and transferring it to an end server, receiving a service provided from the end server and transferring it to the user terminal;
The correction server is
Means for detecting a start timing and an end timing of a service provided by an end server in response to a service request;
Means for calculating a service time based on each detected timing;
Means for notifying the access path server of the service time,
The access path server determines the access timing to the end server permitted to each user terminal using the notified service time as a parameter.   The request reception system according to claim 1, wherein the means for calculating the service time measures an elapsed time from a start timing to an end timing of the service a plurality of times, and uses the moving average as the service time.   3. The request reception system according to claim 2, wherein the service time calculating unit obtains a standard deviation of the elapsed time and excludes an elapsed time exceeding a predetermined range based on the standard deviation. In the request reception method of accepting an access path request transmitted from a user terminal, determining an access timing to an end server permitted to each user terminal, and returning this as an access path to each user terminal,
An access path server that accepts an access path request received from the user terminal and returns an access path response; and
A correction server for receiving a service request from a user terminal and transferring it to an end server, receiving a service provided from the end server and transferring it to the user terminal;
The correction server is
A procedure for detecting a start timing and an end timing of a service provided by an end server in response to a service request;
A procedure for calculating a service time based on each detected timing;
And a procedure for notifying the access path server of the service time,
The access path server determines the access timing to the end server permitted to each user terminal using the notified service time as a parameter.

Images