Adaptation in Convolutionally Coded MIMO-OFDM Wireless Systems Through Supervised Learning and SNR Ordering

Daniels, Robert C.; Caramanis, Constantine; Heath, Robert W.

doi:10.1109/tvt.2009.2029693

Cited by 124 publications

(89 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the set of post process SNRs for all subcarriers is known to be a good metric, the required sample complexity for using such a high dimensional feature set is prohibitive, both in terms of storage and computational power required. This dimensionality problem is solved in [4] by post process SNR ordering and subselecting a particular small subset. In the prediction phase, the k nearest neighbor (kNN) algorithm is used to determine the Packet Error Rate (PER) of new channel realization and the MCS with the highest rate is chosen.…”

Section: A Prior Workmentioning

confidence: 99%

“…We use this PER data to generate random transmissions with success probability of (1-PER). Following the feature set extraction scheme shown in [4], we use four dimensional feature space of ordered post process SNR. For all the performance figures throughout this paper, the x axis represents the sequential index of arriving packets and the y axis represents the relative throuput performance of a given algorithm versus the performance of an ideal algorithm that chooses MCS with the best throuput (i.e.…”

Section: ) Update Rulementioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning for Link Adaptation in MIMO-OFDM Wireless Systems

Yun

Caramanis

2010

2010 IEEE Global Telecommunications Conference GLOBECOM 2010

View full text Add to dashboard Cite

Abstract-Machine learning algorithms have recently attracted much interest for effective link adaptation due to their flexibility and ability to capture more environmental effects implicitly than classical adaptation algorithms. However, past applications are limited to rather simple configurations such as identifying channel condition or link adaptation in fixed or slowly varying channels. Recently, more sophisticated approaches using offline supervised learning have been proposed for link adaptation in complex configurations such as MIMO-OFDM. However, their time complexity and offline training phase hamper their real-world applicability. Approaches using online learning have shown good throughput performance, but the high memory requirement makes them inefficient or even impractical. In this paper, we propose a new effective online learning algorithm for link adaptation. Our computations show that the algorithm performs comparably to the existing online learning approaches, but ours requires minimal storage and time, which makes it more practical. Moreover it adapts to the change of channel distribution quickly.

show abstract

Section: A Prior Workmentioning

confidence: 99%

Section: ) Update Rulementioning

confidence: 99%

Reinforcement Learning for Link Adaptation in MIMO-OFDM Wireless Systems

Yun

Caramanis

2010

2010 IEEE Global Telecommunications Conference GLOBECOM 2010

View full text Add to dashboard Cite

show abstract

“…Recently it was shown that, with sufficient interleaving, coded bit-error rate and the MIMO-OFDM symbol error rate may be evaluated after a sorting operation over subcarriers and spatial streams [4,5]. This observation led to highly accurate link quality metrics of low-dimension.…”

Section: Introductionmentioning

confidence: 99%

“…This observation led to highly accurate link quality metrics of low-dimension. These link quality metrics were exploited by supervised learning algorithms, resulting in new performance benchmarks for MIMO-OFDM link adaptation [5].…”

Section: Introductionmentioning

confidence: 99%