Deep Reinforcement Learning-Based Access Class Barring for Energy-Efficient mMTC Random Access in LTE Networks

Bui, Anh-Tuan H.; Pham, Anh T.

doi:10.1109/access.2020.3045811

Cited by 22 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the performance evaluation section, we validated that the proposed CeRA-eSP exceeded the performance of the existing CeRA scheme with respect to the RA success rate. In future work, we will further improve the preamble selection process using machine learning techniques that have been considered in recent studies [ 19 , 20 , 21 ].…”

Section: Discussionmentioning

confidence: 99%

“…The contention-based RA procedure is a reference method used in the existing RA scheme and it has difficulty supporting massive connectivity. Therefore, a number of studies on contention-based RA considering the massive RA of 5G have been conducted [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 ].…”

Section: Related Workmentioning

confidence: 99%

“…The proposed scheme improved the access success probability through RL-based dynamic barring factor selection. The authors of [ 20 ] studied the ACB method by considering the energy consumption and delay constraints of the device. In this study, a deep reinforcement learning approach was used to obtain the real-time mean barring time and barring rate.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

CeRA-eSP: Code-Expanded Random Access to Enhance Success Probability of Massive MTC

Youn

Park

et al. 2022

Sensors

View full text Add to dashboard Cite

With the growing interest in the Internet of Things (IoT), research on massive machine-type communication (mMTC) services is being actively promoted. Because mMTC services are required to serve a large number of devices simultaneously, a lack of resources during initial access can be a significant problem when providing mMTC services in cellular networks. Various studies on efficient preamble transmission have been conducted to solve the random access problem of mMTC services. However, supporting a large number of devices simultaneously with limited resources is a challenging problem. In this study, we investigate code-expanded random access (CeRA), which extends the limited preamble resources to the code domain to decrease the high collision rate. To solve the existing CeRA phantom codeword and physical uplink shared channel (PUSCH) resource shortage problems, we propose an optimal preamble codeword set selection algorithm based on mathematical analysis. The simulation results indicate that the proposed code-expanded random access scheme to enhance success probability (CeRA-eSP) achieves a higher random access success rate with a lower access delay compared to the existing random access schemes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

CeRA-eSP: Code-Expanded Random Access to Enhance Success Probability of Massive MTC

Youn

Park

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The super-parameters involved in the adjustment include depth of neural network, number of nodes in hidden layer, activation function, learning rate, attenuation coefficient, regularity coefficient, etc. Through the continuous adjustment and optimization of various super-parameters, the training results of different parameter combinations are analyzed and compared, and the better parameter combination is selected [ 22 , 23 ]. When the detailed meteorological data are used as the input data, the input layer will have 91059-dimensional data.…”

Section: Experiments and Analysismentioning

confidence: 99%

Application of Deep Learning Model in Building Energy Consumption Prediction

Wang¹

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to achieve China’s energy conservation and emission reduction goal of peaking carbon dioxide emissions around 2030, it is of great significance. An important means of building energy conservation and emission reduction is the fine management of building energy consumption, which is based on the accurate prediction of building energy consumption, so as to support the optimal management of building operation and achieve the goal of energy conservation and emission reduction. This paper puts forward the evaluation indexes of the results of the building energy consumption prediction model, uses MAPE and RMSE indexes to evaluate the accuracy of the prediction results of the model, and uses the prediction time and input parameter dimensions to evaluate the time cost of the prediction model. Then, using the three building energy consumption prediction models based on machine learning algorithm established above, the prediction of energy consumption of four types of public buildings in different seasons is completed, and the prediction results are evaluated and analyzed. According to the prediction results and the requirements of related work on the accuracy of building energy consumption prediction model, the adaptation relationship between different types of buildings and different machine learning algorithm prediction models is summarized.

show abstract

“…In this context, reinforcement learning methods [22] can be used for slotted ALOHA systems [23]- [27]. In particular, a reinforcement learning based random access was studied to dynamically tune the barring factor and the mean barring time for energy efficient MTCs in LTE systems [24]. In a multi-channel slotted ALOHA, [25] developed a cooperatively trained deep reinforcement learning based controller that depends on the complexity of different random access schemes, in improving the performance of random access control.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for NOMA-ALOHA Under Fading

Choi

2022

IEEE Trans. Commun.

View full text Add to dashboard Cite

We consider a non-orthogonal multiple access in a random-access ALOHA system, in which each user randomly accesses one out of different time slots and send uplink packets based on power differences. In the context of an asymmetric game, we propose a non-orthogonal multiple access ALOHA system based on multi-agent reinforcement learning tools that can help each user to find its best strategies of improving the rates of successful action choices. While taking into account not only collisions, but also fading, we analyze the mean rewards of actions under general settings and focus on the case that involves two different groups of users. To characterize the behaviors of accessing strategies, we apply multi-agent action value methods that consider either greedy or non-greedy actions, combined with an acceleration gradient descent. Our results show that in the proposed system, users employing the greedy action-based methods can be randomly divided into two groups of users and increase the rates of successful action choices. Interestingly, in relatively limited channels, such greedy methods turn many of users to be with a state of barring-access. In this case, the proposed acceleration, non-greedy action methods are shown to reduce such unfairness, at a loss of successful action rates.

show abstract

Deep Reinforcement Learning-Based Access Class Barring for Energy-Efficient mMTC Random Access in LTE Networks

Cited by 22 publications

References 16 publications

CeRA-eSP: Code-Expanded Random Access to Enhance Success Probability of Massive MTC

CeRA-eSP: Code-Expanded Random Access to Enhance Success Probability of Massive MTC

Application of Deep Learning Model in Building Energy Consumption Prediction

Reinforcement Learning for NOMA-ALOHA Under Fading

Contact Info

Product

Resources

About