On the accuracy of smartphone-based mobile network measurement

Li, Weichao; Mok, Ricky K. P.; Wu, Daoyuan; Chang, Rocky K. C.

doi:10.1109/infocom.2015.7218402

Cited by 23 publications

(18 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Comparing the measured variances with the results by Li et al [26], the variances are similar. For the Nexus 5 ±2.331 ms for an RTT of 20 ms and ±0.811 ms for an RTT of 50 ms were determined for processing data packets received on the WiFi interface.…”

Section: Comparison Of the Observed Variances On-device Overheadsupporting

confidence: 80%

See 1 more Smart Citation

Assessing the Implications of Cellular Network Performance on Mobile Content Access

Kaup

Michelinakis

Bui

et al. 2016

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Mobile applications such as VoIP, (live) gaming, or video streaming have diverse QoS requirements ranging from low delay to high throughput. The optimization of the network quality experienced by end-users requires detailed knowledge of the expected network performance. Also, the achieved service quality is affected by a number of factors, including network operator and available technologies. However, most studies measuring the cellular network do not consider the performance implications of network configuration and management. To this end, this paper reports about an extensive data set of cellular network measurements, focused on analyzing root causes of mobile network performance variability. Measurements conducted on a 4G cellular network in Germany show that management and configuration decisions have a substantial impact on the performance. Specifically, it is observed that the association of mobile devices to a Point of Presence (PoP) within the operator's network can influence the end-to-end performance by a large extent. Given the collected data, a model predicting the PoP assignment and its resulting RTT leveraging Markov Chain and machine learning approaches is developed. RTT increases of 58% to 73% compared to the optimum performance are observed in more than 57% of the measurements. Measurements of the response and page load times of popular websites lead to similar results, namely a median increase of 40% between the worst and the best performing PoP.

show abstract

Section: Comparison Of the Observed Variances On-device Overheadsupporting

confidence: 80%

“…Network operations on mobile devices cause an additional, device internal delay, stemming from kernel and operating system processing the outgoing and incoming packets [26]. This delay is different depending on the chosen measurement implementation (e.g.…”

Section: Measurement Methodologymentioning

confidence: 99%

Assessing the Implications of Cellular Network Performance on Mobile Content Access

Kaup

Michelinakis

Bui

et al. 2016

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…The results for the other two phones (not shown here) are very similar. While we agree on the main claims of [29] about overheads, we believe that different technologies require specific tests to evaluate their performance. Thus, each interface should be calibrated separately.…”

Section: Experiments Resultsmentioning

confidence: 52%

“…A few recent papers [15,16] studied endto-end achievable throughput, also accounting for inter-arrival times and passive monitoring techniques, but without comparing their findings with ground-truth readings. The accuracy of WiFi measurements performed by mobile phone is studied in [29] based on a timing analysis. However, their results cannot be applied to our scenario for two reasons: WiFi and LTE differs significantly in terms of scheduling and MAC protocols, and tcpdump traces do not provide a reliable ground truth for the physical radio link.…”

Section: Related Workmentioning

confidence: 99%

Fine-grained LTE radio link estimation for mobile phones

Bui

Michelinakis

Widmer

2018

Pervasive and Mobile Computing

View full text Add to dashboard Cite

Recently, spectrum optimization solutions require mobile phones to obtain precise, accurate and fine-grained estimates of the radio link data rate. In particular, the effectiveness of anticipatory schemes depends on the granularity of these measurements. In this paper we use a reliable LTE control channel sniffer (OWL) to extensively compare mobile phone measurements against exact LTE radio link data rates. We also provide a detailed study of latencies measured on mobile phones, the sniffer, and a server to which the phone is connected. In this study, we show that mobile phones can accurately (if slightly biased) estimate the physical radio link data rate. We highlight the differences among measurements obtained using different mobile phones, communication technologies and protocols. We also provide detailed instructions on how to replicate our measurements and describe alternative measurement setups and their tradeoffs.

show abstract

“…As we discuss below, such delay can potentially impact the accuracy of our method. An attempt to measure a similar delay is presented in [15]. The authors try to measure the delay between the arrival of an IP packet at the WiFi interface, and its registration in the kernel.…”

Section: B Measurement Accuracymentioning

confidence: 99%

Passive Mobile Bandwidth Classification Using Short Lived TCP Connections

Michelinakis¹,

Kreitz²,

Petrocco³

et al. 2015

2015 8th IFIP Wireless and Mobile Networking Conference (WMNC)

View full text Add to dashboard Cite

thereConsumption of multimedia content is moving from a residential environment to mobile phones. Optimizing Quality of Experience-smooth, quick, and high quality playback-is more difficult in this setting, due to the highly dynamic nature of wireless links. A key requirement for achieving this goal is estimating the available bandwidth of mobile devices. Ideally, this should be done quickly and with low overhead. One challenge is that the majority of connections on mobiles are short-lived TCP connections, where a significant portion of data exchange is within the slow start phase. In this paper, we propose a novel method that passively estimates the currently available bandwidth by monitoring the minimal traffic generated by such connections. To the best of our knowledge, no other solution can operate with such constrained input. Our estimation method is able to achieve good precision despite artifacts introduced by the slow start behavior of TCP, mobile scheduler and phone hardware. We evaluate our solution against traces collected in 4 European countries. Furthermore, the small footprint of our algorithm allows its deployment on resource limited devices.

show abstract

On the accuracy of smartphone-based mobile network measurement

Cited by 23 publications

References 14 publications

Assessing the Implications of Cellular Network Performance on Mobile Content Access

Assessing the Implications of Cellular Network Performance on Mobile Content Access

Fine-grained LTE radio link estimation for mobile phones

Passive Mobile Bandwidth Classification Using Short Lived TCP Connections

Contact Info

Product

Resources

About