Presentation | 2023-03-03 DNS Query Log Aggregation Method Based on Co-occuerence Masaki Kobayashi, Akito Suzuki, Masahiro Kobayashi, Tatsuaki Kimura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The complexity of traffic demand fluctuation factors caused by the diversification of user terminals and services has made it difficult to predict traffic demand fluctuations. However, to ensure communication quality, it is necessary to forecast traffic demand appropriately based on the diversified factors and to allocate resources accordingly.In this paper, we focus on the fact that Fully Qualified Domain Name (FQDN) name resolution is performed by the Domain Name System (DNS) before traffic is generated, and aim to accurately predict demand fluctuations by analyzing the time-series variation of DNS queries. Prior research has used NTF (Non-negative Tensor Factorization) to pre-classify query logs.However, prior work is computationally expensive due to the large number of FQDNs contained in the logs, and prior aggregation is required.In this paper, we propose a method for FQDN aggregation by focusing on the co-occurrence of DNS queries. The proposed method defines the degree of similarity between FQDNs based on the co-occurrence of DNS queries, and constructs a graph with FQDNs as nodes and the degree of similarity between them as branches. The graph is then aggregated by using community analysis to extract FQDNs that are highly similar to each other. The results of the evaluation using the logs of DNS servers installed in a university network show that the proposed method improves the accuracy of traffic demand prediction. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | DNS / Community Analysis / Traffic Prediction |
Paper # | IN2022-118 |
Date of Issue | 2023-02-23 (IN) |
Conference Information | |
Committee | IN / NS |
---|---|
Conference Date | 2023/3/2(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Convention Centre + Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | General |
Chair | Kunio Hato(Internet Multifeed) / Tetsuya Oishi(NTT) |
Vice Chair | Tsutomu Murase(Nagoya Univ.) / Takumi Miyoshi(Shibaura Insti of Tech.) |
Secretary | Tsutomu Murase(KDDI Research) / Takumi Miyoshi(Nagaoka Univ. of Tech.) |
Assistant | / Kotaro Mihara(NTT) |
Paper Information | |
Registration To | Technical Committee on Information Networks / Technical Committee on Network Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | DNS Query Log Aggregation Method Based on Co-occuerence |
Sub Title (in English) | |
Keyword(1) | DNS |
Keyword(2) | Community Analysis |
Keyword(3) | Traffic Prediction |
1st Author's Name | Masaki Kobayashi |
1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
2nd Author's Name | Akito Suzuki |
2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
3rd Author's Name | Masahiro Kobayashi |
3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
4th Author's Name | Tatsuaki Kimura |
4th Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2023-03-03 |
Paper # | IN2022-118 |
Volume (vol) | vol.122 |
Number (no) | IN-407 |
Page | pp.pp.311-316(IN), |
#Pages | 6 |
Date of Issue | 2023-02-23 (IN) |