Presentation | 2020-12-18 Performance evaluation of using image processing by Fog Computing Shintaro Hirose, Takafumi Hayashi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | With the spread of IoT and the advent of 5G, the amount of data handled on the Internet has become huge. Due to the increase in communication traffic and demand for low-latency messaging, the current mainstream of cloud computing will reach its limits, and it will be necessary to migrate to a new network architecture. In this situation, Fog Computing, as proposed by Cisco, is considered to be one of the solutions to these problems. This concept places a fog server between the cloud and the user to perform distributed processing, which prevents the concentration of data processing and enables us to deal with increasing data traffic. In this paper, we evaluate the inference performance of a machine learning model that interacts with fog and cloud. We experiment using Docker to prepare fog nodes and clouds with different amounts of memory, and change the communication path to simulate a server machine as a fog and cloud. We compare the processing time between fog and cloud based on the regional object detection model, and the processing time by the input format using the image classification model, and report on the usefulness of fog use and effective input formats in image processing inference. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Fog Computing / TensorFlow Serving / Base64 / Performance evaluation |
Paper # | NS2020-107 |
Date of Issue | 2020-12-10 (NS) |
Conference Information | |
Committee | NS / RCS |
---|---|
Conference Date | 2020/12/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Multi-hop/Relay/Cooperation, Disaster-resistant wireless network, Sensor/Mesh network, Ad-hoc network, D2D/M2M, Wireless network coding, Handover/AP switching/Connected cell control/Load balancing among base stations/Mobile network dynamic reconfiguration, QoS/QoE assurance, Wireless VoIP, IoT, Edge computing, etc. |
Chair | Akihiro Nakao(Univ. of Tokyo) / Eiji Okamoto(Nagoya Inst. of Tech.) |
Vice Chair | Tetsuya Oishi(NTT) / Fumiaki Maehara(Waseda Univ.) / Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) |
Secretary | Tetsuya Oishi(NTT) / Fumiaki Maehara(Chuo Univ.) / Toshihiko Nishimura(Kyushu Univ.) / Tomoya Tandai(NEC) |
Assistant | Shinya Kawano(NTT) / Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) |
Paper Information | |
Registration To | Technical Committee on Network Systems / Technical Committee on Radio Communication Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Performance evaluation of using image processing by Fog Computing |
Sub Title (in English) | |
Keyword(1) | Fog Computing |
Keyword(2) | TensorFlow Serving |
Keyword(3) | Base64 |
Keyword(4) | Performance evaluation |
1st Author's Name | Shintaro Hirose |
1st Author's Affiliation | Niigata University(Niigata Univ.) |
2nd Author's Name | Takafumi Hayashi |
2nd Author's Affiliation | Nihon University(Nihon Univ.) |
Date | 2020-12-18 |
Paper # | NS2020-107 |
Volume (vol) | vol.120 |
Number (no) | NS-297 |
Page | pp.pp.108-112(NS), |
#Pages | 5 |
Date of Issue | 2020-12-10 (NS) |