Tao Liu, Alberto E. Cerpa
As an integral part of reliable communication in wireless networks, effective link estimation is essential for routing protocols. However, due to the dynamic nature of wireless channels, accurate link quality estimation remains a challenging task. In this paper, we propose 4C, a novel link estimator that applies link quality prediction along with link estimation. Our approach is data-driven and consists of three steps: data collection, off-line modeling and on-line prediction. The data collection step involves gathering link quality data, and based on our analysis of the data, we pro- pose a set of guidelines for the amount of data to be collected in our experimental scenarios. The modeling step includes off-line prediction model training and selection. We present three prediction models that utilize different ma- chine learning methods, namely, naive Bayes classifier, logistic regression and artificial neural networks. Our models take a combination of PRR and the physical layer information, i.e., Received Signal Strength Indicator (RSSI), Signal to Noise Ratio (SNR) and Link Quality Indicator (LQI) as input, and output the success probability of delivering the next packet. From our analysis and experiments, we find that logistic regression works well among the three models with small computational cost. Finally, the third step involves the implementation of 4C, a receiver-initiated on-line link quality prediction module that computes the short temporal link quality. We conducted extensive experiments in the Motelab and our local indoor testbeds, as well as an outdoor deployment. Our results with single and multiple senders experiments show that with 4C, CTP improves the average cost of delivering a packet by 20% to 30%. In some cases, the improvement is larger than 45%.
Tao Liu, Alberto E. Cerpa, "Foresee (4C): Wireless link prediction using link features," Proceedings of the Tenth ACM/IEEE International Conference on Information Processing on Sensor Networks (IPSN 2011), pp. 294--305, Chicago, IL, USA, April, 2011.
@Conference{Liu11a,
author = "Tao Liu and Alberto E. Cerpa",
booktitle = "Proceedings of the Tenth ACM/IEEE International
Conference on Information Processing on Sensor Networks
(IPSN 2011)",
title = "Foresee (4{C}): Wireless link prediction using link
features",
year = "2011",
month = apr,
pages = "294--305",
address = "Chicago, IL, USA",
keywords = "4C link estimator;Foresee;Motelab;artificial neural
networks;data collection;link features;link quality
estimation;link quality indicator;logistic
regression;machine learning methods;naive Bayes
classifier;off-line modeling;on-line
prediction;physical layer information;received signal
strength indicator;receiver-initiated on-line link
quality prediction module;reliable
communication;routing protocols;short temporal link
quality;signal to noise ratio;wireless
channels;wireless link prediction;wireless
networks;learning (artificial intelligence);neural
nets;radio links;radio networks;routing
protocols;telecommunication network reliability;",
URL = "http://www.andes.ucmerced.edu/papers/Liu11a.pdf",
accept = "20",
cited = "19",
}