WO2022038788A1 - Estimation device, estimation method, and program - Google Patents

Estimation device, estimation method, and program Download PDF

Info

Publication number
WO2022038788A1
WO2022038788A1 PCT/JP2020/031726 JP2020031726W WO2022038788A1 WO 2022038788 A1 WO2022038788 A1 WO 2022038788A1 JP 2020031726 W JP2020031726 W JP 2020031726W WO 2022038788 A1 WO2022038788 A1 WO 2022038788A1
Authority
WO
WIPO (PCT)
Prior art keywords
waiting time
display waiting
estimation
web
cumulative probability
Prior art date
Application number
PCT/JP2020/031726
Other languages
French (fr)
Japanese (ja)
Inventor
崇 寺内
則次 恵木
和久 山岸
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 PCT/JP2020/031726 priority Critical patent/WO2022038788A1/en
Publication of WO2022038788A1 publication Critical patent/WO2022038788A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment

Definitions

  • the present invention relates to an estimation device, an estimation method and a program.
  • the delay time of packet transmission increases, fluctuation (jitter) occurs, and packet loss occurs, so that the amount of data transmitted related to Web browsing. Decreases, and the Web display waiting time increases. Further, for example, if the bandwidth allocated to the network is low, it leads to an increase in the Web display waiting time. As a result of these, the quality of experience of the user who uses Web browsing may deteriorate.
  • Patent Documents 1 and 2 are known as conventional techniques related to a method for evaluating Web browsing quality from network quality.
  • the quality evaluation method described in Patent Document 1 is a method of estimating the Web display waiting time from the information observable in the network.
  • the quality evaluation method described in Patent Document 2 is a web browsing quality based on the relationship between the web display waiting time and the quality index value (QoE: Quality of Experience) corresponding to the quality experienced by the user. Is a method of estimating.
  • QoE Quality of Experience
  • the relationship between the one-way delay time and the cumulative probability of the Web display waiting time is as shown in FIG. 1, and the relationship between the packet loss rate and the cumulative probability of the Web display waiting time is shown in FIG.
  • FIG. 1 and 2 show the cumulative probability of the Web display waiting time under the condition that a certain one-way delay time or a certain packet loss rate occurs.
  • a cumulative probability of 0.8 and a Web display waiting time of about 6500 are associated with a packet loss rate of 1%, which means that 80% of users display the Web on the Web under the condition of a packet loss rate of 1%. It means that the waiting time is within about 6500 ms.
  • the actual Web display waiting time differs for each user (that is, when the packet loss rate is 1%).
  • the Web display waiting time of each user is widely distributed between about 4000 m and about 9000 ms.)
  • the average Web display waiting time is calculated from the network quality parameter representing the network quality (for example, throughput)
  • this difference in distribution can be expressed.
  • the distribution of the Web display waiting time may be concentrated in the vicinity of the average value in each one-way delay time, but the method described in Patent Document 1 described above may have an average value. If they are the same, the same average Web display waiting time is calculated, so that the difference in distribution cannot be expressed.
  • One embodiment of the present invention has been made in view of the above points, and an object thereof is to estimate the generation distribution of the Web display waiting time.
  • the estimation device displays a website when a parameter representing the network quality is input and Web browsing is performed via a network in which the network quality is represented by the parameter.
  • the Web display waiting time estimation device 10 capable of estimating the relationship between the Web display waiting time and the cumulative probability thereof will be described.
  • the provider of the network service can know the occurrence distribution of the Web display waiting time, so that it becomes possible to realize the network design and control in consideration of the occurrence distribution.
  • the Web display waiting time is the waiting time from requesting information on a certain website to displaying the information on the Web browser on the Web browser when using Web browsing. Is.
  • FIG. 3 is a diagram showing an example of the functional configuration of the Web display waiting time estimation device 10 according to the present embodiment.
  • the Web display waiting time estimation device 10 has a waiting time characteristic estimation unit 101 and a waiting time characteristic visualization unit 102.
  • the waiting time characteristic estimation unit 101 inputs a network quality parameter representing the network quality of the target network (for example, (for example) one-way delay time, fluctuation (jitter), packet loss rate, etc., in whole or in part), and wait time characteristics. Based on the estimation model, the relational expression between the Web display waiting time and its cumulative probability is derived. Then, the waiting time characteristic estimation unit 101 outputs the derived relational expression to the waiting time characteristic visualization unit 102.
  • the target network is a network for which the Web display waiting time is estimated, and is a network that is passed between the user's terminal (client) and the server that provides the information of the website when using the web browsing. Is. The waiting time characteristic estimation model will be described later.
  • the waiting time characteristic visualization unit 102 receives the relational expression derived by the waiting time characteristic estimation unit 101 as an input, and outputs the relational information showing the relationship between the Web display waiting time and the cumulative probability thereof.
  • Examples of such related information include a graph in which the Web display waiting time is on the vertical axis and the cumulative probability thereof on the horizontal axis, and a chart showing the Web display waiting time for each occurrence probability at regular intervals.
  • the network quality parameter is a parameter related to one-way delay time, jitter, and packet loss rate.
  • the one-way delay time or the packet loss rate increases, the data transmission rate decreases exponentially, and as a result, the Web display waiting time increases exponentially.
  • the base Web display waiting time W' is calculated by, for example, the following equation 1.
  • D represents a one-way delay time [ms]
  • J represents a jitter [ms]
  • P represents a packet loss rate [%].
  • a 1 , a 2 , a 3 , a 4 , a 5 , a 6 and a 7 are coefficients.
  • the Web display waiting time increases as the one-way delay time increases, but the Web display waiting time at each one-way delay time is almost the average value.
  • the packet loss rate as shown in FIG. 2, as the packet loss rate increases, the Web display waiting time increases and the dispersion also increases.
  • the average packet loss rate is P for a finite number of target packets
  • the probability of occurrence of the actual packet loss rate P'for the target packet is a normal distribution with a constant variance value for the average P. ..
  • the cumulative distribution for this normal distribution (packet loss rate generation distribution) is as shown in FIG. Therefore, the relationship between the cumulative probability A and the packet loss rate P'in this cumulative distribution is approximated as shown in Equation 2 below.
  • b 1 and b 2 are coefficients.
  • P'approximate in the above number 2 is used as an alternative value of P in the above number 1. Further, it is assumed that the packet loss rate due to the overflow of the jitter absorption buffer has the same tendency.
  • the packet loss rate and The relationship between the cumulative probability A and the Web display waiting time W can be expressed by the following number 3 in consideration of the dispersion of jitter (that is, the following number 3 is the waiting time characteristic estimation model).
  • a 1 , a 2 , a 3 , a 4 , a 5 , a 6 , a 7 , b 1 , b 2 , c 1 and c 2 are coefficients.
  • Step 1 A network whose network quality parameter is a certain condition (D, j, pl) is reproduced by a simulator, and Web browsing between a server and a client via this network and measurement of the Web display waiting time are repeated. And get a lot of measurement results.
  • the website used in this measurement a plurality of major websites may be used, or if there is a major website in the target network, only that website may be used.
  • Procedure 2 Next, the above-mentioned large amount of measurement results are sorted in ascending order, and data showing the correspondence between the cumulative probability A and the Web display waiting time W for the condition (D, j, pl) is acquired.
  • Step 3 The above steps 1 and 2 are repeated under various conditions (D, j, pl), and the correspondence between the cumulative probability A and the Web display waiting time W for various conditions (D, j, pl). A large amount of data indicating the above is acquired, and these data are applied to the above number 3 to calculate the Web display waiting time W. Then, for each data, the coefficients a 1 , a 2 , a 3 , a 4 , a 5 , a 6 , a so that the square error between the measurement result corresponding to the data and the Web display waiting time W is minimized. 7 , b 1 , b 2 , c 1 and c 2 are calculated.
  • a waiting time characteristic estimation model can be obtained as a cumulative distribution function or probability distribution function of the web display waiting time based on any formula that expresses the characteristics between the network quality and the probability of occurrence of the web display waiting time. May be good.
  • FIG. 5 is a flowchart showing an example of the Web display waiting time estimation process according to the present embodiment.
  • the waiting time characteristic estimation unit 101 inputs a network quality parameter representing the network quality of the target network (step S101).
  • the waiting time characteristic estimation unit 101 uses the network quality parameter input in step S101 above and the waiting time characteristic estimation model corresponding to this network quality parameter to obtain the Web display waiting time and its cumulative probability. Derivation of the relational expression of (step S102). That is, for example, when the network quality parameter is a parameter related to one-way delay time, jitter, and packet loss rate, the waiting time characteristic estimation unit 101 has the coefficients a 1 , a 2 , of the waiting time characteristic estimation model shown in the above equation 3.
  • the relational expression is derived by calculating a3, a4 , a5 , a6 , a7 , b1 , b2 , c1 and c2. As a result, the relationship between the Web display waiting time when using Web browsing and the cumulative probability thereof is estimated.
  • the relational expression derived by the waiting time characteristic estimation unit 101 is output to the waiting time characteristic visualization unit 102.
  • the waiting time characteristic visualization unit 102 takes the relational expression derived in the above step S102 as an input, and outputs the relational information of this relational expression (step S103). That is, the waiting time characteristic visualization unit 102 displays, for example, a graph with the Web display waiting time on the vertical axis and the cumulative probability thereof on the horizontal axis, a chart showing the Web display waiting time for each occurrence probability at regular intervals, and the like. As a result, the distribution (occurrence distribution) of the Web display waiting time and the occurrence probability thereof when using Web browsing is visualized.
  • FIG. 6 is a diagram showing an example of the hardware configuration of the Web display waiting time estimation device 10 according to the present embodiment.
  • the Web display waiting time estimation device 10 is realized by a general computer or a computer system, and the hardware includes an input device 201, a display device 202, and an external I / F 203. , Communication I / F 204, processor 205, and memory device 206. Each of these hardware is communicably connected via bus 207.
  • the input device 201 is, for example, a keyboard, a mouse, a touch panel, or the like.
  • the display device 202 is, for example, a display or the like.
  • the Web display waiting time estimation device 10 may not have at least one of the input device 201 and the display device 202.
  • the external I / F 203 is an interface with an external device such as a recording medium 203a.
  • the Web display waiting time estimation device 10 can read or write the recording medium 203a via the external I / F 203.
  • one or more programs that realize each functional unit (waiting time characteristic estimation unit 101 and waiting time characteristic visualization unit 102) of the Web display waiting time estimation device 10 may be stored in the recording medium 203a.
  • the recording medium 203a includes, for example, a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), a USB (Universal Serial Bus) memory card, and the like.
  • the communication I / F 204 is an interface for connecting the Web display waiting time estimation device 10 to the communication network.
  • One or more programs that realize each functional unit of the Web display waiting time estimation device 10 may be acquired (downloaded) from a predetermined server device or the like via the communication I / F 204.
  • the processor 205 is, for example, various arithmetic units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). Each functional unit of the Web display waiting time estimation device 10 is realized, for example, by a process of causing the processor 205 to execute one or more programs stored in the memory device 206.
  • a CPU Central Processing Unit
  • a GPU Graphics Processing Unit
  • the memory device 206 is, for example, various storage devices such as HDD (Hard Disk Drive), SSD (Solid State Drive), RAM (Random Access Memory), ROM (Read Only Memory), and flash memory.
  • HDD Hard Disk Drive
  • SSD Solid State Drive
  • RAM Random Access Memory
  • ROM Read Only Memory
  • the Web display waiting time estimation device 10 can realize the above-mentioned Web display waiting time estimation process by having the hardware configuration shown in FIG.
  • the hardware configuration shown in FIG. 6 is an example, and the Web display waiting time estimation device 10 may have another hardware configuration.
  • the Web display waiting time estimation device 10 may have a plurality of processors 205 or a plurality of memory devices 206.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

An estimation device according to an embodiment is characterized by including an estimation unit that receives, as an input, a parameter indicating network quality and estimates the display waiting times of web sites and the cumulative probability of the probabilities of occurrence of the display waiting times in a case where web browsing is performed via a network, with the network quality thereof being indicated by the parameter, and a visualization unit for visualizing the distribution of the display waiting times on the basis of the display waiting times and the cumulative probability that are estimated by the estimation unit.

Description

推定装置、推定方法及びプログラムEstimator, estimation method and program
　本発明は、推定装置、推定方法及びプログラムに関する。 The present invention relates to an estimation device, an estimation method and a program.
　インターネットの普及に伴って、ネットワーク介したＷｅｂブラウジングが広く利用されている。Ｗｅｂブラウジング利用時には、Ｗｅｂブラウザが搭載された端末と閲覧先のＷｅｂサイトを提供するサーバとの間のネットワーク状態によっては、Ｗｅｂブラウザ上にＷｅｂサイトの情報が表示されるまでの待ち時間（以下、「Ｗｅｂ表示待ち時間」ともいう。）が増加し、ユーザの体感品質が低下することがある。 With the spread of the Internet, web browsing via networks is widely used. When using web browsing, depending on the network status between the terminal equipped with the web browser and the server that provides the website to be browsed, the waiting time until the website information is displayed on the web browser (hereinafter referred to as "waiting time"). (Also referred to as “Web display waiting time”) may increase, and the user's perceived quality may deteriorate.
　具体的には、例えば、ネットワークの輻輳等により、パケット伝送の遅延時間が増加したり、揺らぎ（ジッタ）が発生したり、更にはパケット損失が発生したりすることで、Ｗｅｂブラウジングに関するデータ伝送量が低下し、Ｗｅｂ表示待ち時間が増加する。また、例えば、ネットワークに割り当てられている帯域幅が低ければＷｅｂ表示待ち時間の増加に繋がる。これらの結果として、Ｗｅｂブラウジングを利用するユーザの体感品質が低下することがある。 Specifically, for example, due to network congestion or the like, the delay time of packet transmission increases, fluctuation (jitter) occurs, and packet loss occurs, so that the amount of data transmitted related to Web browsing. Decreases, and the Web display waiting time increases. Further, for example, if the bandwidth allocated to the network is low, it leads to an increase in the Web display waiting time. As a result of these, the quality of experience of the user who uses Web browsing may deteriorate.
　このため、ネットワークサービスの提供者が、良好な品質でＷｅｂブラウジングが利用可能なネットワーク設計や制御を行うためには、ネットワークの状態とＷｅｂブラウジング利用時のユーザの体感品質との関係を明らかにし、ネットワークサービスが満たすべきネットワーク品質（片道遅延時間、揺らぎ、パケット損失率、スループット等）の条件を明らかにすることが重要である。 Therefore, in order for the network service provider to design and control the network so that Web browsing can be used with good quality, the relationship between the network status and the user's perceived quality when using Web browsing is clarified. It is important to clarify the conditions of network quality (one-way delay time, fluctuation, packet loss rate, throughput, etc.) that network services must meet.
　ネットワーク品質からＷｅｂブラウジング品質を評価する手法に関連する従来技術として、特許文献１及び２が知られている。特許文献１に記載されている品質評価法は、ネットワーク内で観測可能な情報からＷｅｂ表示待ち時間を推定する手法である。また、特許文献２に記載されている品質評価法は、Ｗｅｂ表示待ち時間とユーザが体感する品質に対応する品質指標値（ＱｏＥ：Quality of Experience）との間にある関係に基づいたＷｅｂブラウジング品質を推定する手法である。 Patent Documents 1 and 2 are known as conventional techniques related to a method for evaluating Web browsing quality from network quality. The quality evaluation method described in Patent Document 1 is a method of estimating the Web display waiting time from the information observable in the network. Further, the quality evaluation method described in Patent Document 2 is a web browsing quality based on the relationship between the web display waiting time and the quality index value (QoE: Quality of Experience) corresponding to the quality experienced by the user. Is a method of estimating.
特開２０１９－１４０４３８号公報Japanese Unexamined Patent Publication No. 2019-140438 特開２０１７－９７６０５号公報JP-A-2017-97605
　しかしながら、従来技術では、Ｗｅｂ表示待ち時間の発生分布を推定することができなかった。このため、例えば、Ｗｅｂ表示待ち時間の発生分布を考慮したネットワーク設計や制御を実現することができなかった。 However, with the conventional technology, it was not possible to estimate the distribution of Web display waiting time. Therefore, for example, it has not been possible to realize network design and control in consideration of the generation distribution of the Web display waiting time.
　例えば、片道遅延時間とＷｅｂ表示待ち時間の累積確率との関係が図１に示されるようなものであり、パケット損失率とＷｅｂ表示待ち時間の累積確率との関係が図２に示されるようなものであったとする。図１及び図２では或る片道遅延時間又は或るパケット損失率が発生した条件下におけるＷｅｂ表示待ち時間の累積確率を表している。例えば、図２ではパケット損失率１％において累積確率０．８とＷｅｂ表示待ち時間約６５００とが対応付けられており、これは、パケット損失率１％の条件下では８０％のユーザがＷｅｂ表示待ち時間約６５００ｍｓ以内に収まることを表している。 For example, the relationship between the one-way delay time and the cumulative probability of the Web display waiting time is as shown in FIG. 1, and the relationship between the packet loss rate and the cumulative probability of the Web display waiting time is shown in FIG. Suppose it was a thing. 1 and 2 show the cumulative probability of the Web display waiting time under the condition that a certain one-way delay time or a certain packet loss rate occurs. For example, in FIG. 2, a cumulative probability of 0.8 and a Web display waiting time of about 6500 are associated with a packet loss rate of 1%, which means that 80% of users display the Web on the Web under the condition of a packet loss rate of 1%. It means that the waiting time is within about 6500 ms.
　このとき、図２に示されるように、同じネットワーク品質劣化（例えば、パケット損失率１％）であっても、実際のＷｅｂ表示待ち時間はユーザ毎に異なる（つまり、パケット損失率１％の場合、各ユーザのＷｅｂ表示待ち時間は約４０００ｍ～約９０００ｍｓの間に広く分布している。）。一方で、上記の特許文献１に記載されている手法では、ネットワーク品質（例えば、スループット）を表すネットワーク品質パラメータから平均Ｗｅｂ表示待ち時間を算出しているため、この分布の違いを表現することができない。すなわち、図１に示されるように、各片道遅延時間において平均値近傍にＷｅｂ表示待ち時間の分布が集中している場合もあり得るが、上記の特許文献１に記載されている手法では平均値が同じであれば同一の平均Ｗｅｂ表示待ち時間が算出されるため、分布の違いを表現することができない。 At this time, as shown in FIG. 2, even if the same network quality deterioration (for example, packet loss rate 1%), the actual Web display waiting time differs for each user (that is, when the packet loss rate is 1%). , The Web display waiting time of each user is widely distributed between about 4000 m and about 9000 ms.) On the other hand, in the method described in Patent Document 1 above, since the average Web display waiting time is calculated from the network quality parameter representing the network quality (for example, throughput), this difference in distribution can be expressed. Can not. That is, as shown in FIG. 1, the distribution of the Web display waiting time may be concentrated in the vicinity of the average value in each one-way delay time, but the method described in Patent Document 1 described above may have an average value. If they are the same, the same average Web display waiting time is calculated, so that the difference in distribution cannot be expressed.
　Ｗｅｂ表示待ち時間の分布が広いものの方が同一の平均Ｗｅｂ表示待ち時間に対し、長い待ち時間となっているユーザが多いため、そのネットワーク品質を優先的に改善する必要があるが、平均Ｗｅｂ表示待ち時間からはその判断が困難である。 Many users have a longer waiting time for the same average Web display waiting time if the distribution of Web display waiting time is wide, so it is necessary to preferentially improve the network quality. It is difficult to judge from the waiting time.
　本発明の一実施形態は、上記の点に鑑みてなされたもので、Ｗｅｂ表示待ち時間の発生分布を推定することを目的とする。 One embodiment of the present invention has been made in view of the above points, and an object thereof is to estimate the generation distribution of the Web display waiting time.
　上記目的を達成するため、一実施形態に係る推定装置は、ネットワーク品質を表すパラメータを入力として、前記パラメータによって前記ネットワーク品質が表されるネットワークを経由するＷｅｂブラウジングを行った場合におけるＷｅｂサイトの表示待ち時間と、前記表示待ち時間の発生確率の累積確率とを推定する推定部と、前記推定部により推定された前記表示待ち時間と前記累積確率とに基づいて、前記表示待ち時間の分布を可視化する可視化部と、を有することを特徴とする。 In order to achieve the above object, the estimation device according to the embodiment displays a website when a parameter representing the network quality is input and Web browsing is performed via a network in which the network quality is represented by the parameter. Visualize the distribution of the display waiting time based on the estimation unit that estimates the waiting time and the cumulative probability of the occurrence probability of the display waiting time, and the display waiting time and the cumulative probability estimated by the estimation unit. It is characterized by having a visualization unit and a visualization unit.
　Ｗｅｂ表示待ち時間の発生分布を推定することができる。 It is possible to estimate the distribution of Web display waiting time.
片道遅延時間とＷｅｂ表示待ち時間の累積確率との関係の一例を説明するための図である。It is a figure for demonstrating an example of the relationship between the one-way delay time and the cumulative probability of the Web display waiting time. パケット損失率とＷｅｂ表示待ち時間の累積確率との関係の一例を説明するための図である。It is a figure for demonstrating an example of the relationship between the packet loss rate and the cumulative probability of the Web display waiting time. 本実施形態に係るＷｅｂ表示待ち時間推定装置の機能構成の一例を示す図である。It is a figure which shows an example of the functional structure of the Web display waiting time estimation apparatus which concerns on this embodiment. パケット損失率の累積分布関数モデルの一例を説明するための図である。It is a figure for demonstrating an example of the cumulative distribution function model of a packet loss rate. 本実施形態に係るＷｅｂ表示待ち時間推定処理の一例を示すフローチャートである。It is a flowchart which shows an example of the Web display waiting time estimation process which concerns on this Embodiment. 本実施形態に係るＷｅｂ表示待ち時間推定装置のハードウェア構成の一例を示す図である。It is a figure which shows an example of the hardware configuration of the Web display waiting time estimation apparatus which concerns on this embodiment.
　以下、本発明の一実施形態について説明する。本実施形態では、Ｗｅｂ表示待ち時間とその累積確率との関係を推定することができるＷｅｂ表示待ち時間推定装置１０について説明する。これにより、例えば、ネットワークサービスの提供者はＷｅｂ表示待ち時間の発生分布を知ることができるため、当該発生分布を考慮したネットワーク設計や制御を実現することができるようになる。なお、Ｗｅｂ表示待ち時間とは、上述したように、Ｗｅｂブラウジング利用時に、或るＷｅｂサイトの情報を要求してから、Ｗｅｂブラウザ上に当該Ｗｅｂサイトの情報が表示されるまでの待ち時間のことである。 Hereinafter, an embodiment of the present invention will be described. In the present embodiment, the Web display waiting time estimation device 10 capable of estimating the relationship between the Web display waiting time and the cumulative probability thereof will be described. As a result, for example, the provider of the network service can know the occurrence distribution of the Web display waiting time, so that it becomes possible to realize the network design and control in consideration of the occurrence distribution. As described above, the Web display waiting time is the waiting time from requesting information on a certain website to displaying the information on the Web browser on the Web browser when using Web browsing. Is.
　＜Ｗｅｂ表示待ち時間推定装置１０の機能構成＞
　まず、本実施形態に係るＷｅｂ表示待ち時間推定装置１０の機能構成について、図３を参照しながら説明する。図３は、本実施形態に係るＷｅｂ表示待ち時間推定装置１０の機能構成の一例を示す図である。 <Functional configuration of Web display waiting time estimation device 10>
First, the functional configuration of the Web display waiting time estimation device 10 according to the present embodiment will be described with reference to FIG. FIG. 3 is a diagram showing an example of the functional configuration of the Web display waiting time estimation device 10 according to the present embodiment.
　図３に示すように、本実施形態に係るＷｅｂ表示待ち時間推定装置１０は、待ち時間特性推定部１０１と、待ち時間特性可視化部１０２とを有する。 As shown in FIG. 3, the Web display waiting time estimation device 10 according to the present embodiment has a waiting time characteristic estimation unit 101 and a waiting time characteristic visualization unit 102.
　待ち時間特性推定部１０１は、対象ネットワークのネットワーク品質（例えば、（平均）片道遅延時間、揺らぎ（ジッタ）、パケット損失率等の全部又は一部）を表すネットワーク品質パラメータを入力として、待ち時間特性推定モデルに基づいて、Ｗｅｂ表示待ち時間とその累積確率との関係式を導出する。そして、待ち時間特性推定部１０１は、導出した関係式を待ち時間特性可視化部１０２に出力する。なお、対象ネットワークとはＷｅｂ表示待ち時間の推定対象とするネットワークのことであり、Ｗｅｂブラウジング利用時にユーザの端末（クライアント）とＷｅｂサイトの情報を提供するサーバとの間で経由されるネットワークのことである。待ち時間特性推定モデルについては後述する。 The waiting time characteristic estimation unit 101 inputs a network quality parameter representing the network quality of the target network (for example, (for example) one-way delay time, fluctuation (jitter), packet loss rate, etc., in whole or in part), and wait time characteristics. Based on the estimation model, the relational expression between the Web display waiting time and its cumulative probability is derived. Then, the waiting time characteristic estimation unit 101 outputs the derived relational expression to the waiting time characteristic visualization unit 102. The target network is a network for which the Web display waiting time is estimated, and is a network that is passed between the user's terminal (client) and the server that provides the information of the website when using the web browsing. Is. The waiting time characteristic estimation model will be described later.
　待ち時間特性可視化部１０２は、待ち時間特性推定部１０１によって導出された関係式を入力として、Ｗｅｂ表示待ち時間とその累積確率との関係を表す関係情報を出力する。ここで、このような関係情報としては、例えば、Ｗｅｂ表示待ち時間を縦軸、その累積確率を横軸としたグラフ、一定間隔の発生確率毎のＷｅｂ表示待ち時間を表す図表等が挙げられる。 The waiting time characteristic visualization unit 102 receives the relational expression derived by the waiting time characteristic estimation unit 101 as an input, and outputs the relational information showing the relationship between the Web display waiting time and the cumulative probability thereof. Here, examples of such related information include a graph in which the Web display waiting time is on the vertical axis and the cumulative probability thereof on the horizontal axis, and a chart showing the Web display waiting time for each occurrence probability at regular intervals.
　ここで、ネットワーク品質パラメータは片道遅延時間、ジッタ及びパケット損失率に関するパラメータであるものとした場合における待ち時間特性推定モデルの一例について説明する。一般に、片道遅延時間やパケット損失率が増加した場合、データ伝送率は指数的に低下し、その結果としてＷｅｂ表示待ち時間は指数的に増加する。ジッタの影響はジッタ吸収バッファあふれによるパケット損失率の増加に繋がるものとすれば、ベースとなるＷｅｂ表示待ち時間Ｗ'は、例えば、以下の数１により算出される。 Here, an example of a waiting time characteristic estimation model will be described when the network quality parameter is a parameter related to one-way delay time, jitter, and packet loss rate. In general, when the one-way delay time or the packet loss rate increases, the data transmission rate decreases exponentially, and as a result, the Web display waiting time increases exponentially. Assuming that the influence of jitter leads to an increase in the packet loss rate due to the overflow of the jitter absorption buffer, the base Web display waiting time W'is calculated by, for example, the following equation 1.
Figure JPOXMLDOC01-appb-M000001
 　ただし、Ｄは片道遅延時間［ｍｓ］、Ｊはジッタ［ｍｓ］、Ｐはパケット損失率［％］を表す。また、ａ１，ａ２，ａ３，ａ４，ａ５，ａ６及びａ７は係数である。
Figure JPOXMLDOC01-appb-M000001
 However, D represents a one-way delay time [ms], J represents a jitter [ms], and P represents a packet loss rate [%]. Further, a 1 , a 2 , a 3 , a 4 , a 5 , a 6 and a 7 are coefficients.
　片道遅延時間の場合、図１に示されるように、片道遅延時間の増加と共にＷｅｂ表示待ち時間は増大するものの、各片道遅延時間におけるＷｅｂ表示待ち時間はほぼその平均値近傍となる。一方で、パケット損失率の場合は、図２に示されるように、パケット損失率の増加と共に、Ｗｅｂ表示待ち時間が増加すると共にその分散も大きくなる。例えば、有限個の対象パケットに対して平均パケット損失率がＰであった場合、対象パケットに対する実際のパケット損失率Ｐ'の発生確率は平均Ｐに対して一定の分散値を持つ正規分布となる。また、この正規分布（パケット損失率の発生分布）に対する累積分布は図４のようになる。そこで、この累積分布における累積確率Ａとパケット損失率Ｐ'との関係を以下の数２のように近似する。 In the case of the one-way delay time, as shown in FIG. 1, the Web display waiting time increases as the one-way delay time increases, but the Web display waiting time at each one-way delay time is almost the average value. On the other hand, in the case of the packet loss rate, as shown in FIG. 2, as the packet loss rate increases, the Web display waiting time increases and the dispersion also increases. For example, if the average packet loss rate is P for a finite number of target packets, the probability of occurrence of the actual packet loss rate P'for the target packet is a normal distribution with a constant variance value for the average P. .. The cumulative distribution for this normal distribution (packet loss rate generation distribution) is as shown in FIG. Therefore, the relationship between the cumulative probability A and the packet loss rate P'in this cumulative distribution is approximated as shown in Equation 2 below.
Figure JPOXMLDOC01-appb-M000002
 　ただし、ｂ１及びｂ２は係数である。
Figure JPOXMLDOC01-appb-M000002
 However, b 1 and b 2 are coefficients.
　そして、上記の数２で近似したＰ'を、上記の数１中のＰの代替値として利用する。また、ジッタ吸収バッファあふれによるパケット損失率についても同様の傾向を持つものとする。 Then, P'approximate in the above number 2 is used as an alternative value of P in the above number 1. Further, it is assumed that the packet loss rate due to the overflow of the jitter absorption buffer has the same tendency.
　このとき、パケット損失率がｐｌであった場合における対象パケットに対する実際のパケット損失率をＰ'、ジッタがｊであった場合における対象ジッタに対する実際のジッタをＪ'とすれば、パケット損失率及びジッタの分散を考慮した以下の数３により、累積確率ＡとＷｅｂ表示待ち時間Ｗとの関係を表すことができる（つまり、以下の数３が待ち時間特性推定モデルである。）。 At this time, if the actual packet loss rate for the target packet when the packet loss rate is pl is P'and the actual jitter for the target jitter when the jitter is j is J', the packet loss rate and The relationship between the cumulative probability A and the Web display waiting time W can be expressed by the following number 3 in consideration of the dispersion of jitter (that is, the following number 3 is the waiting time characteristic estimation model).
Figure JPOXMLDOC01-appb-M000003
 　ただし、ａ１，ａ２，ａ３，ａ４，ａ５，ａ６，ａ７，ｂ１，ｂ２，ｃ１及びｃ２は係数である。これらの係数を算出することにより、Ｗｅｂ表示待ち時間とその累積確率との関係式が導出される。
Figure JPOXMLDOC01-appb-M000003
 However, a 1 , a 2 , a 3 , a 4 , a 5 , a 6 , a 7 , b 1 , b 2 , c 1 and c 2 are coefficients. By calculating these coefficients, the relational expression between the Web display waiting time and the cumulative probability thereof is derived.
　上記の各係数については、例えば、以下の手順１～手順３により算出される。 Each of the above coefficients is calculated by, for example, the following procedures 1 to 3.
　手順１：ネットワーク品質パラメータが或る条件（Ｄ，ｊ，ｐｌ）であるネットワークをシミュレータにより再現し、このネットワークを経由するサーバ及びクライアント間のＷｅｂブラウジングとそのＷｅｂ表示待ち時間の測定とを繰り返し行って、大量の測定結果を取得する。なお、この測定で用いるＷｅｂサイトについては、複数の主要なＷｅｂサイトを利用してもよいし、対象ネットワークにおいて主要なＷｅｂサイトがあればそのＷｅｂサイトのみを利用してもよい。 Step 1: A network whose network quality parameter is a certain condition (D, j, pl) is reproduced by a simulator, and Web browsing between a server and a client via this network and measurement of the Web display waiting time are repeated. And get a lot of measurement results. As the website used in this measurement, a plurality of major websites may be used, or if there is a major website in the target network, only that website may be used.
　手順２：次に、上記の大量の測定結果を昇順に並び替え、当該条件（Ｄ，ｊ，ｐｌ）に対する累積確率ＡとＷｅｂ表示待ち時間Ｗとの対応関係を示すデータを取得する。 Procedure 2: Next, the above-mentioned large amount of measurement results are sorted in ascending order, and data showing the correspondence between the cumulative probability A and the Web display waiting time W for the condition (D, j, pl) is acquired.
　手順３：上記の手順１及び手順２を様々な条件（Ｄ，ｊ，ｐｌ）で繰り返し行って、様々な条件（Ｄ，ｊ，ｐｌ）に対する累積確率ＡとＷｅｂ表示待ち時間Ｗとの対応関係を示すデータを大量に取得し、これらのデータを上記の数３に適用してＷｅｂ表示待ち時間Ｗを算出する。そして、各データに関して、当該データに対応する測定結果とＷｅｂ表示待ち時間Ｗとの二乗誤差が最小となるように、係数ａ１，ａ２，ａ３，ａ４，ａ５，ａ６，ａ７，ｂ１，ｂ２，ｃ１及びｃ２を算出する。 Step 3: The above steps 1 and 2 are repeated under various conditions (D, j, pl), and the correspondence between the cumulative probability A and the Web display waiting time W for various conditions (D, j, pl). A large amount of data indicating the above is acquired, and these data are applied to the above number 3 to calculate the Web display waiting time W. Then, for each data, the coefficients a 1 , a 2 , a 3 , a 4 , a 5 , a 6 , a so that the square error between the measurement result corresponding to the data and the Web display waiting time W is minimized. 7 , b 1 , b 2 , c 1 and c 2 are calculated.
　なお、上記の数１～数３は一例であって、待ち時間特性推定モデルは、これに限られない。ネットワーク品質とＷｅｂ表示待ち時間の発生確率との間にある特性を表す式であれば任意の式に基づいてＷｅｂ表示待ち時間の累積分布関数や確率分布関数として待ち時間特性推定モデルが得られてもよい。 Note that the above numbers 1 to 3 are examples, and the waiting time characteristic estimation model is not limited to this. A waiting time characteristic estimation model can be obtained as a cumulative distribution function or probability distribution function of the web display waiting time based on any formula that expresses the characteristics between the network quality and the probability of occurrence of the web display waiting time. May be good.
　＜Ｗｅｂ表示待ち時間推定処理＞
　次に、本実施形態に係るＷｅｂ表示待ち時間推定処理について、図５を参照しながら説明する。図５は、本実施形態に係るＷｅｂ表示待ち時間推定処理の一例を示すフローチャートである。 <Web display waiting time estimation process>
Next, the Web display waiting time estimation process according to the present embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an example of the Web display waiting time estimation process according to the present embodiment.
　まず、待ち時間特性推定部１０１は、対象ネットワークのネットワーク品質を表すネットワーク品質パラメータを入力する（ステップＳ１０１）。 First, the waiting time characteristic estimation unit 101 inputs a network quality parameter representing the network quality of the target network (step S101).
　次に、待ち時間特性推定部１０１は、上記のステップＳ１０１で入力されたネットワーク品質パラメータと、このネットワーク品質パラメータに対応する待ち時間特性推定モデルとを用いて、Ｗｅｂ表示待ち時間とその累積確率との関係式を導出する（ステップＳ１０２）。すなわち、例えば、ネットワーク品質パラメータが片道遅延時間、ジッタ及びパケット損失率に関するパラメータである場合、待ち時間特性推定部１０１は、上記の数３に示す待ち時間特性推定モデルの係数ａ１，ａ２，ａ３，ａ４，ａ５，ａ６，ａ７，ｂ１，ｂ２，ｃ１及びｃ２を算出することで当該関係式を導出する。これにより、Ｗｅｂブラウジング利用時のＷｅｂ表示待ち時間とその累積確率との関係が推定される。なお、待ち時間特性推定部１０１によって導出された関係式は待ち時間特性可視化部１０２に出力される。 Next, the waiting time characteristic estimation unit 101 uses the network quality parameter input in step S101 above and the waiting time characteristic estimation model corresponding to this network quality parameter to obtain the Web display waiting time and its cumulative probability. Derivation of the relational expression of (step S102). That is, for example, when the network quality parameter is a parameter related to one-way delay time, jitter, and packet loss rate, the waiting time characteristic estimation unit 101 has the coefficients a 1 , a 2 , of the waiting time characteristic estimation model shown in the above equation 3. The relational expression is derived by calculating a3, a4 , a5 , a6 , a7 , b1 , b2 , c1 and c2. As a result, the relationship between the Web display waiting time when using Web browsing and the cumulative probability thereof is estimated. The relational expression derived by the waiting time characteristic estimation unit 101 is output to the waiting time characteristic visualization unit 102.
　そして、待ち時間特性可視化部１０２は、上記のステップＳ１０２で導出された関係式を入力として、この関係式の関係情報を出力する（ステップＳ１０３）。すなわち、待ち時間特性可視化部１０２は、例えば、Ｗｅｂ表示待ち時間を縦軸、その累積確率を横軸としたグラフ、一定間隔の発生確率毎のＷｅｂ表示待ち時間を表す図表等を表示する。これにより、Ｗｅｂブラウジング利用時のＷｅｂ表示待ち時間及びその発生確率の分布（発生分布）が可視化される。 Then, the waiting time characteristic visualization unit 102 takes the relational expression derived in the above step S102 as an input, and outputs the relational information of this relational expression (step S103). That is, the waiting time characteristic visualization unit 102 displays, for example, a graph with the Web display waiting time on the vertical axis and the cumulative probability thereof on the horizontal axis, a chart showing the Web display waiting time for each occurrence probability at regular intervals, and the like. As a result, the distribution (occurrence distribution) of the Web display waiting time and the occurrence probability thereof when using Web browsing is visualized.
　＜Ｗｅｂ表示待ち時間推定装置１０のハードウェア構成＞
　最後に、本実施形態に係るＷｅｂ表示待ち時間推定装置１０のハードウェア構成について、図６を参照しながら説明する。図６は、本実施形態に係るＷｅｂ表示待ち時間推定装置１０のハードウェア構成の一例を示す図である。 <Hardware configuration of Web display waiting time estimation device 10>
Finally, the hardware configuration of the Web display waiting time estimation device 10 according to the present embodiment will be described with reference to FIG. FIG. 6 is a diagram showing an example of the hardware configuration of the Web display waiting time estimation device 10 according to the present embodiment.
　図６に示すように、本実施形態に係るＷｅｂ表示待ち時間推定装置１０は一般的なコンピュータ又はコンピュータシステムで実現され、ハードウェアとして、入力装置２０１と、表示装置２０２と、外部Ｉ／Ｆ２０３と、通信Ｉ／Ｆ２０４と、プロセッサ２０５と、メモリ装置２０６とを有する。これらの各ハードウェアは、それぞれがバス２０７を介して通信可能に接続されている。 As shown in FIG. 6, the Web display waiting time estimation device 10 according to the present embodiment is realized by a general computer or a computer system, and the hardware includes an input device 201, a display device 202, and an external I / F 203. , Communication I / F 204, processor 205, and memory device 206. Each of these hardware is communicably connected via bus 207.
　入力装置２０１は、例えば、キーボードやマウス、タッチパネル等である。表示装置２０２は、例えば、ディスプレイ等である。なお、Ｗｅｂ表示待ち時間推定装置１０は、入力装置２０１及び表示装置２０２のうちの少なくとも一方を有していなくてもよい。 The input device 201 is, for example, a keyboard, a mouse, a touch panel, or the like. The display device 202 is, for example, a display or the like. The Web display waiting time estimation device 10 may not have at least one of the input device 201 and the display device 202.
　外部Ｉ／Ｆ２０３は、記録媒体２０３ａ等の外部装置とのインタフェースである。Ｗｅｂ表示待ち時間推定装置１０は、外部Ｉ／Ｆ２０３を介して、記録媒体２０３ａの読み取りや書き込み等を行うことができる。記録媒体２０３ａには、例えば、Ｗｅｂ表示待ち時間推定装置１０が有する各機能部（待ち時間特性推定部１０１及び待ち時間特性可視化部１０２）を実現する１以上のプログラムが格納されていてもよい。なお、記録媒体２０３ａには、例えば、ＣＤ（Compact Disc）、ＤＶＤ（Digital Versatile Disk）、ＳＤメモリカード（Secure Digital memory card）、ＵＳＢ（Universal Serial Bus）メモリカード等がある。 The external I / F 203 is an interface with an external device such as a recording medium 203a. The Web display waiting time estimation device 10 can read or write the recording medium 203a via the external I / F 203. For example, one or more programs that realize each functional unit (waiting time characteristic estimation unit 101 and waiting time characteristic visualization unit 102) of the Web display waiting time estimation device 10 may be stored in the recording medium 203a. The recording medium 203a includes, for example, a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), a USB (Universal Serial Bus) memory card, and the like.
　通信Ｉ／Ｆ２０４は、Ｗｅｂ表示待ち時間推定装置１０を通信ネットワークに接続するためのインタフェースである。なお、Ｗｅｂ表示待ち時間推定装置１０が有する各機能部を実現する１以上のプログラムは、通信Ｉ／Ｆ２０４を介して、所定のサーバ装置等から取得（ダウンロード）されてもよい。 The communication I / F 204 is an interface for connecting the Web display waiting time estimation device 10 to the communication network. One or more programs that realize each functional unit of the Web display waiting time estimation device 10 may be acquired (downloaded) from a predetermined server device or the like via the communication I / F 204.
　プロセッサ２０５は、例えば、ＣＰＵ（Central Processing Unit）やＧＰＵ（Graphics Processing Unit）等の各種演算装置である。Ｗｅｂ表示待ち時間推定装置１０が有する各機能部は、例えば、メモリ装置２０６に格納されている１以上のプログラムがプロセッサ２０５に実行させる処理により実現される。 The processor 205 is, for example, various arithmetic units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). Each functional unit of the Web display waiting time estimation device 10 is realized, for example, by a process of causing the processor 205 to execute one or more programs stored in the memory device 206.
　メモリ装置２０６は、例えば、ＨＤＤ（Hard Disk Drive）やＳＳＤ（Solid State Drive）、ＲＡＭ（Random Access Memory）、ＲＯＭ（Read Only Memory）、フラッシュメモリ等の各種記憶装置である。 The memory device 206 is, for example, various storage devices such as HDD (Hard Disk Drive), SSD (Solid State Drive), RAM (Random Access Memory), ROM (Read Only Memory), and flash memory.
　本実施形態に係るＷｅｂ表示待ち時間推定装置１０は、図６に示すハードウェア構成を有することにより、上述したＷｅｂ表示待ち時間推定処理を実現することができる。なお、図６に示すハードウェア構成は一例であって、Ｗｅｂ表示待ち時間推定装置１０は、他のハードウェア構成を有していてもよい。例えば、Ｗｅｂ表示待ち時間推定装置１０は、複数のプロセッサ２０５を有していてもよいし、複数のメモリ装置２０６を有していてもよい。 The Web display waiting time estimation device 10 according to the present embodiment can realize the above-mentioned Web display waiting time estimation process by having the hardware configuration shown in FIG. The hardware configuration shown in FIG. 6 is an example, and the Web display waiting time estimation device 10 may have another hardware configuration. For example, the Web display waiting time estimation device 10 may have a plurality of processors 205 or a plurality of memory devices 206.
　本発明は、具体的に開示された上記の実施形態に限定されるものではなく、請求の範囲の記載から逸脱することなく、種々の変形や変更、既知の技術との組み合わせ等が可能である。 The present invention is not limited to the above-described embodiment specifically disclosed, and various modifications and modifications, combinations with known techniques, and the like are possible without departing from the description of the claims. ..
　１０　　　　Ｗｅｂ表示待ち時間推定装置
　１０１　　　待ち時間特性推定部
　１０２　　　待ち時間特性可視化部
　２０１　　　入力装置
　２０２　　　表示装置
　２０３　　　外部Ｉ／Ｆ
　２０３ａ　　記録媒体
　２０４　　　通信Ｉ／Ｆ
　２０５　　　プロセッサ
　２０６　　　メモリ装置
　２０７　　　バス 10 Web display waiting time estimation device 101 Waiting time characteristic estimation unit 102 Waiting time characteristic visualization unit 201 Input device 202 Display device 203 External I / F
203a Recording medium 204 Communication I / F
205 Processor 206 Memory Device 207 Bus

Claims (7)

  1. 　ネットワーク品質を表すパラメータを入力として、前記パラメータによって前記ネットワーク品質が表されるネットワークを経由するＷｅｂブラウジングを行った場合におけるＷｅｂサイトの表示待ち時間と、前記表示待ち時間の発生確率の累積確率とを推定する推定部と、
    　前記推定部により推定された前記表示待ち時間と前記累積確率とに基づいて、前記表示待ち時間の分布を可視化する可視化部と、
    　を有することを特徴とする推定装置。     Using a parameter representing the network quality as an input, the display waiting time of the website and the cumulative probability of the occurrence probability of the display waiting time when browsing the Web via the network in which the network quality is represented by the parameter are input. The estimation unit to estimate and
    A visualization unit that visualizes the distribution of the display waiting time based on the display waiting time estimated by the estimation unit and the cumulative probability.
    An estimation device characterized by having.
  2. 　前記パラメータには、片道遅延時間、ジッタ及びパケット損失率の全部又は一部が含まれる、ことを特徴とする請求項１に記載の推定装置。 The estimation device according to claim 1, wherein the parameters include all or part of a one-way delay time, jitter, and a packet loss rate.
  3. 　前記推定部は、
    　前記ネットワーク品質に関する特定の条件下で前記Ｗｅｂブラウジングを行った場合における前記表示待ち時間及び累積確率との関係を表すモデル式により、前記表示待ち時間と前記累積確率とを推定する、ことを特徴とする請求項１又は２に記載の推定装置。     The estimation unit
    The feature is that the display waiting time and the cumulative probability are estimated by a model formula representing the relationship between the display waiting time and the cumulative probability when the Web browsing is performed under specific conditions related to the network quality. The estimation device according to claim 1 or 2.
  4. 　ネットワーク品質を表すパラメータを入力として、前記パラメータによって前記ネットワーク品質が表されるネットワークを経由するＷｅｂブラウジングを行った場合におけるＷｅｂサイトの表示待ち時間と、前記表示待ち時間の発生確率の累積確率とを推定する推定手順と、
    　前記推定手順で推定された前記表示待ち時間と前記累積確率とに基づいて、前記表示待ち時間の分布を可視化する可視化手順と、
    　をコンピュータが実行することを特徴とする推定方法。     Using a parameter representing the network quality as an input, the display waiting time of the website and the cumulative probability of the occurrence probability of the display waiting time when browsing the Web via the network in which the network quality is represented by the parameter are input. Estimating procedure to estimate and
    A visualization procedure for visualizing the distribution of the display waiting time based on the display waiting time estimated by the estimation procedure and the cumulative probability.
    An estimation method characterized by a computer performing.
  5. 　前記パラメータには、片道遅延時間、ジッタ及びパケット損失率の全部又は一部が含まれる、ことを特徴とする請求項４に記載の推定方法。 The estimation method according to claim 4, wherein the parameters include all or part of a one-way delay time, jitter, and a packet loss rate.
  6. 　前記推定手順は、
    　前記ネットワーク品質に関する特定の条件下で前記Ｗｅｂブラウジングを行った場合における前記表示待ち時間及び累積確率との関係を表すモデル式により、前記表示待ち時間と前記累積確率とを推定する、ことを特徴とする請求項４又は５に記載の推定方法。     The estimation procedure is
    The feature is that the display waiting time and the cumulative probability are estimated by a model formula representing the relationship between the display waiting time and the cumulative probability when the Web browsing is performed under specific conditions related to the network quality. The estimation method according to claim 4 or 5.
  7. 　コンピュータを、請求項１乃至３の何れか一項に記載の推定装置として機能させるプログラム。 A program that causes a computer to function as the estimation device according to any one of claims 1 to 3.
PCT/JP2020/031726 2020-08-21 2020-08-21 Estimation device, estimation method, and program WO2022038788A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/031726 WO2022038788A1 (en) 2020-08-21 2020-08-21 Estimation device, estimation method, and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/031726 WO2022038788A1 (en) 2020-08-21 2020-08-21 Estimation device, estimation method, and program

Publications (1)

Publication Number Publication Date
WO2022038788A1 true WO2022038788A1 (en) 2022-02-24

Family

ID=80322606

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/031726 WO2022038788A1 (en) 2020-08-21 2020-08-21 Estimation device, estimation method, and program

Country Status (1)

Country Link
WO (1) WO2022038788A1 (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019235101A1 (en) * 2018-06-04 2019-12-12 日本電信電話株式会社 Time-adding method, time-adding device, and program

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019235101A1 (en) * 2018-06-04 2019-12-12 日本電信電話株式会社 Time-adding method, time-adding device, and program

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
AIDA, MASAKI; MIYOSHI, NAOTO; ISHIBASHI, KEISUKE; KURIBAYASHI, SHIN-ICHI: "On Mathematical Formulation of CoMPACT Monitor for Nonstationary User Traffic", IEICE TECHNICAL REPORT, vol. 102, no. 565 (IN2002-177), 10 January 2003 (2003-01-10), JP , pages 59 - 64, XP009534893, ISSN: 0913-5685 *
OGAWA, HIDEKI; KAWANO, TAICHI; IKEGAMI, DAISUKE: "A Study on Web Performance Estimation with NW Performance Considering Content Characteristics", IEICE TECHNICAL REPORT, vol. 118, no. 503 (CQ2018-112), 7 March 2019 (2019-03-07), JP , pages 105 - 109, XP009534892, ISSN: 2432-6380 *

Similar Documents

Publication Publication Date Title
US10796319B2 (en) Rating aggregation and propagation mechanism for hierarchical services and products
EP3230867B1 (en) Browser provided website statistics
US7817578B2 (en) Method for integrating downstream performance and resource usage statistics into load balancing weights
US9436729B2 (en) Information retrieval system evaluation method, device and storage medium
CN108111430B (en) TCP initial window optimization method and system
US20050257167A1 (en) Embedded Web dialog
CN116672721B (en) Game popularization webpage real-time management method and system
CN110889725A (en) Online advertisement CTR estimation method, device, equipment and storage medium
JP5112277B2 (en) Reproduction processing method, computer system, and program
US8307011B2 (en) System and method for determining overall utilization
US20210266384A1 (en) Critical path estimation for accelerated and optimal loading of web pages
WO2022038788A1 (en) Estimation device, estimation method, and program
WO2019244507A1 (en) Quality estimation device, quality estimation method, and program
JP7003909B2 (en) Communication analysis device, communication analysis method and computer program
US10944631B1 (en) Network request and file transfer prioritization based on traffic elasticity
CN117221148A (en) System and method for evaluating service quality of multi-type network application
US9183042B2 (en) Input/output traffic backpressure prediction
Cheng et al. Modeling and Application of Grey Model GM (2, 1) Based on Linear Difference Equation.
JP5623336B2 (en) Resource usage rate calculation device, response time ratio calculation device, resource usage rate calculation method, and program
JP2011186712A (en) Performance analysis apparatus, performance analysis method and performance analysis program
JP6239195B2 (en) Performance evaluation apparatus and performance evaluation program
JP6307026B2 (en) Web performance estimation apparatus, web performance estimation system, and web performance estimation method
JP2018195198A (en) Providing device, providing method, and providing program
JP5325280B2 (en) Information processing device
US11749297B2 (en) Audio quality estimation apparatus, audio quality estimation method and program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20950353

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20950353

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP