On Medium and Long Term Channel Conditions Prediction for Mobile Devices

Wang, Xiaoli; Grinshpun, Edward; Faucher, David; Sharma, Sameer

doi:10.1109/wcnc.2017.7925951

Cited by 5 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where C (b i ) is the average number of useful bits per PRB for bearer i [31]. The forecast of the UEs channel quality can be used to estimate the MCS [24].…”

Section: Objectivementioning

confidence: 99%

RAN Resource Usage Prediction for a 5G Slice Broker

Gutterman

Grinshpun

Sharma

et al. 2019

Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing

Self Cite

View full text Add to dashboard Cite

Network slicing will allow 5G network operators to oer a diverse set of services over a shared physical infrastructure. We focus on supporting the operation of the Radio Access Network (RAN) slice broker, which maps slice requirements into allocation of Physical Resource Blocks (PRBs). We rst develop a new metric, REVA, based on the number of PRBs available to a single Very Active bearer. REVA is independent of channel conditions and allows easy derivation of an individual wireless link's throughput. In order for the slice broker to eciently utilize the RAN, there is a need for reliable and short term prediction of resource usage by a slice. To support such prediction, we construct an LTE testbed and develop custom additions to the scheduler. Using data collected from the testbed, we compute REVA and develop a realistic time series prediction model for REVA. Specically, we present the X-LSTM prediction model, based upon Long Short-Term Memory (LSTM) neural networks. Evaluated with data collected in the testbed, X-LSTM outperforms Autoregressive Integrated Moving Average Model (ARIMA) and LSTM neural networks by up to 31%. X-LSTM also achieves over 91% accuracy in predicting REVA. By using X-LSTM to predict future usage, a slice broker is more adept to provision a slice and reduce over-provisioning and SLA violation costs by more than 10% in comparison to LSTM and ARIMA. CCS CONCEPTS• Networks → Wireless access points, base stations and infrastructure; • Computing methodologies → Neural networks;

show abstract

“…where C (b i ) is the average number of useful bits per PRB for bearer i [31]. The forecast of the UEs channel quality can be used to estimate the MCS [24].…”

Section: Objectivementioning

confidence: 99%

RAN Resource Usage Prediction for a 5G Slice Broker

Gutterman

Grinshpun

Sharma

et al. 2019

Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Instead of only looking at the current state of network and video player, we also predict the evolution of channel quality while determining our buffering strategy. Wang et al present a channel quality predictor based on machine learning techniques [17]. They target real-time applications but not consider a specific application like we do.…”

Section: Related Workmentioning

confidence: 99%

Improving Mobile Video Quality Through Predictive Channel Quality Based Buffering

Kleinrouweler

Meixner

Bosman

et al. 2018

2018 30th International Teletraffic Congress (ITC 30)

View full text Add to dashboard Cite

Frequent variations in throughput make mobile networks a challenging environment for video streaming. Current video players deal with those variations by matching video quality to network throughput. However, this adaptation strategy results in frequent changes of video resolution and bitrate, which negatively impacts the users' streaming experience. Alternatively, keeping the video quality constant would improve the experience, but puts additional demand on the network. Downloading high quality content when channel quality is low requires additional resources, because data transfer efficiency is linked to channel quality. In this paper, we present a predictive Channel Quality based Buffering Strategy (CQBS) that lets the video buffer grow when channel quality is good, and relies on this buffer when channel quality decreases. Our strategy is the outcome of a Markov Decision Process. The underlying Markov chain is conditioned on 377 real-world LTE channel quality traces that we have collected using an Android mobile application. With our strategy, mobile network providers can deliver constant quality video streams, using less network resources.

show abstract