Hardware Efficient Massive MIMO Detector Based on the Monte Carlo Tree Search Method

Chen, Jienan; Chao, Fei; Lu, Hao; Sobelman, Gerald E.; Hu, Jianhao

doi:10.1109/jetcas.2017.2743458

Cited by 9 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2017, Chen et al (2017) proposed the MCTS for the MIMO detector for the purpose of decision-making and for game-playing problems. Thus, BER and the complexity were reduced.…”

Section: Literature Reviewmentioning

confidence: 99%

Review on various detectors in massive MIMO technology: a performance analysis

Manju

Ganesh

2021

IJPCC

View full text Add to dashboard Cite

Purpose Multiple-input multiple-output (MIMO) combined with multi-user massive MIMO has been a well-known approach for high spectral efficiency in wideband systems, and it was targeted to detect the MIMO signals. The increasing data rates with multiple antennas and multiple users that share the communication channel simultaneously lead to higher capacity requirements and increased complexity. Thus, different detection algorithms were developed for the Massive MIMO. Design/methodology/approach This paper focuses on the various literature analyzes on various detection algorithms and techniques for MIMO detectors. Here, it reviews several research papers and exhibits the significance of each detection method. Findings This paper provides the details of the performance analysis of the MIMO detectors and reveals the best value in the case of each performance measure. Finally, it widens the research issues that can be useful for future researchers to be accomplished in MIMO massive detectors Originality/value This paper has presented a detailed review of the detection of massive MIMO on different algorithms and techniques. The survey mainly focuses on different types of channels used in MIMO detections, the number of antennas used in transmitting signals from the source to destination, and vice-versa. The performance measures and the best performance of each of the detectors are described.

show abstract

“…In 2017, Chen et al (2017) proposed the MCTS for the MIMO detector for the purpose of decision-making and for game-playing problems. Thus, BER and the complexity were reduced.…”

Section: Literature Reviewmentioning

confidence: 99%

Review on various detectors in massive MIMO technology: a performance analysis

Manju

Ganesh

2021

IJPCC

View full text Add to dashboard Cite

show abstract

“…Tree search algorithms are also used in detectors [14]- [18], where the MIMO detection problem is formulated as a decision tree and a symbol is recovered at each layer of the tree. In [19], a statistical approach with the Monte Carlo tree search (MCTS) algorithm was proposed with hardware acceleration to recover the transmitted symbols at large MIMO setups. Other nonlinear methods such as belief propagation (BP) [20], [21], semidefinite relaxation (SDR) [22], and approximate message passing (AMP) [23] are all able to achieve good performance under many practical scenarios, while having lower complexity than the ML detector.…”

Section: A Related Workmentioning

confidence: 99%

“…It is worth noting that, comparing Table III and Table IV, the complexity of DRL-MCTS significantly reduces while that of DRL and MCTS both increase in this larger antenna system. The increased complexity for DRL and MCTS results from calculating the reward value of larger matrices for each move [19] and the function operations of higher-dimensional matrices. The main reason for the reduced complexity for DRL-MCTS is the reduced playout number required.…”

Section: Computational Complexitymentioning

confidence: 99%

Deep Reinforcement Learning Aided Monte Carlo Tree Search for MIMO Detection

Mo,

Chang,

Kan

2021

Preprint

View full text Add to dashboard Cite

This paper proposes a novel multiple-input multipleoutput (MIMO) symbol detector that incorporates a deep reinforcement learning (DRL) agent into the Monte Carlo tree search (MCTS) detection algorithm. We first describe how the MCTS algorithm, used in many decision-making problems, is applied to the MIMO detection problem. Then, we introduce a self-designed deep reinforcement learning agent, consisting of a policy value network and a state value network, which is trained to detect MIMO symbols. The outputs of the trained networks are adopted into a modified MCTS detection algorithm to provide useful node statistics and facilitate enhanced tree search process. The resulted scheme, termed the DRL-MCTS detector, demonstrates significant improvements over the original MCTS detection algorithm and exhibits favorable performance compared to other existing linear and DNN-based detection methods under varying channel conditions.

show abstract

Low Cost LSTM Implementation based on Stochastic Computing for Channel State Information Prediction

Wang

Liu

et al. 2018

2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)

View full text Add to dashboard Cite

Hardware Efficient Massive MIMO Detector Based on the Monte Carlo Tree Search Method

Cited by 9 publications

References 26 publications

Review on various detectors in massive MIMO technology: a performance analysis

Review on various detectors in massive MIMO technology: a performance analysis

Deep Reinforcement Learning Aided Monte Carlo Tree Search for MIMO Detection

Low Cost LSTM Implementation based on Stochastic Computing for Channel State Information Prediction

Contact Info

Product

Resources

About