On Weather and Internet Traffic Demand - Technical Report
The weather is known to have a major impact on demand of utilities such as electricity or gas. Given that the Internet usage is strongly tied with human activity, one could guess the existence of similar correlation between its traffic demand and the weather conditions. In this paper, empirical in n...
| Autores: | , , |
|---|---|
| Tipo de documento: | relatório científico |
| Data de publicação: | 2012 |
| País: | España |
| Recursos: | IMDEA Networks Institute |
| Repositório: | IMDEA Networks Institute Digital Repository |
| Idioma: | inglês |
| OAI Identifier: | oai:dspace.networks.imdea.org:20.500.12761/1142 |
| Acesso em linha: | http://hdl.handle.net/20.500.12761/1142 https://dx.doi.org/TR-Institute IMDEA-Networks-2012-3 |
| Access Level: | Acceso aberto |
| Palavra-chave: | Q Science::Q Science (General) Q Science::QA Mathematics::QA75 Electronic computers. Computer science T Technology::T Technology (General) T Technology::TA Engineering (General). Civil engineering (General) T Technology::TK Electrical engineering. Electronics Nuclear engineering |
| Resumo: | The weather is known to have a major impact on demand of utilities such as electricity or gas. Given that the Internet usage is strongly tied with human activity, one could guess the existence of similar correlation between its traffic demand and the weather conditions. In this paper, empirical in nature, we demonstrate and quantify such correlation between weather conditions and the Internet traffic demand on different time-scales (from hourly to yearly). For that purpose we collect and use the data from 8 Internet eXchange Points (IXP), geographically spread on 5 different continents, as indicators of the Internet demand in those particular areas. We observe that the seasonal traffic demand variability exists in the locations with large yearly variations in temperature, while the traffic demand in locations close to the equator (with low variability of temperature) is season independent. Using a fine-grain dataset, from three European IXPs, we show that precipitation increases the traffic demand for up to 6%, and somewhat surprisingly that in regards to the impact of precipitation on the demand all major types of ISPs (mobile, residential, content, etc.) observe very similar behavior. One of the implications of the observed time-of-the-day dependent impact of the precipitation is that precipitation has a mild impact on the IP transit costs. Finally, we hint on the possible benefits of the seasonal variations on the energy-proportional computing and scheduling large-scale software releases. |
|---|