Network Fortune Cookie: Using Network Measurements to Predict Video Streaming Performance and QoE
| Autor: | William Lautenschlager, Luciano Paschoal Gaspary, Roberto Iraja Tavares da Costa Filho, Nicolas Silveira Kagami, Valter Roesler |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
business.industry computer.internet_protocol Quality of service media_common.quotation_subject Real-time computing Telecommunications service 020206 networking & telecommunications Throughput 02 engineering and technology Internet protocol suite Scalability 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Quality (business) Performance indicator business computer Computer network media_common |
| Zdroj: | GLOBECOM |
| Popis: | Due to the fact that video streaming is the current "killer" application and for competitiveness, telecommunication service providers need to be able to answer a fundamental question: to which extent is the available network infrastructure able to successfully provide users with a satisfactory experience when running video streaming applications? Answering this question is far from trivial because existing techniques are neither scalable nor accurate enough. To address this issue, we propose a model to predict video streaming quality based on the observation of performance indicators of the underlying IP network. To accomplish this objective, the proposed model - created using LTE networks as case study - leverages low network consumption active measurements and machine learning techniques. Obtained results show that the proposed solution produces accurate estimates (average error of less than 10%) while keeping intrusiveness around twenty times lower than traditional techniques. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|