Generation of realistic cloud access times for mobile application testing using transfer learning

نویسندگان

چکیده

The network Quality of Service (QoS) metrics such as the access time, bandwidth, and packet loss play an important role in determining Experience (QoE) mobile applications. Various factors like Radio Resource Control (RRC) states, Mobile Network Operator (MNO) specific retransmission configurations, handovers triggered by user mobility, load, etc. can cause high variability these QoS on 4G/LTE, WiFi networks, which be detrimental to application QoE. Therefore, exposing realistic is critical for a tester attempting predict its A viable approach testing using synthetic traces. main challenge generation traces diversity environments lack wide scope real calibrate generators. In this paper, we describe measurement-driven methodology based transfer learning with Long Short Term Memory (LSTM) neural nets solve problem. requires relatively short sample targeted environment adapt presented basic model new environments, thus simplifying generation. We present feature LTE cloud time models adapted diverse target trace size just 6000 samples measured over few tens minutes. demonstrate that generated from are capable accurately reproducing QoE metric distributions including their outlier values.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Towards Cloud Mobile Hybrid Application Generation using Semantically Enriched DSL

The advancements in computing have resulted in a boom of cheap, ubiquitous, connected mobile devices as well as seemingly unlimited, utility style, pay as you go computing resources, commonly referred to as Cloud computing. Taking advantage of this computing landscape, however, has been hampered by the many heterogeneities that exist in the mobile space as well as the Cloud space. This research...

متن کامل

‏‎facilitating lexical access for the fluent production of speech‎‏

‏‎the hypothesis is that recent and frequent exposure to lexical items leads to a more fluent production of speech in terms of rate of speech. to test the hypothesis , a one- way anova experimental design was carried out. 24 senior student of efl participated in a one-way interview test. data analyses revealed that those who were exposed frequently to the lexical items over a week prior to inte...

15 صفحه اول

‏‎faciliting lexical access for the fluent production of speech‎‏

‏‎the hypothesis is that recent and frequent exposure to lexical items leads to a more fluent production of speech in terms of rate of speech. to test the hypothesis,a one-way anova experimental design was carried out. 24 sednior students of efl participated in a one-way interview test. data analyses revealed that those who were exposed frequently to the lexical items over a week prior to inter...

15 صفحه اول

A Mobile Learning Application to Access Learning Objects

The concept of learning object appears as a mean to improve the reuse of educational resources in digital format.The Sharable Content Object Reference Model (SCORM) is a common model for learning objects that makes easy the reutilization of educational contents between different systems. The objective of this paper is to show how an educational content in form of learning object packaged under ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Computer Communications

سال: 2021

ISSN: ['1873-703X', '0140-3664']

DOI: https://doi.org/10.1016/j.comcom.2021.03.010