KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Search Results

Now showing 1 - 10 of 36

Some of the metrics are blocked by your
consent settings
Deep Learning-Based Channel Estimation With 1D CNN for OFDM Systems Under High-Speed Railway Environments
(2025-01-01)
Siriwanitpong, Aphitchaya
;
Sanada, Kosuke
;
Hatano, Hiroyuki
;
Mori, Kazuo
;
Boonsrimuang, Pisit
In OFDM wireless communications, channel estimation performance is compromised in high-speed railway environments owing to extremely fast multipath fading and severe Doppler effect. Recently, a deep learning approach has been employed to improve the channel estimation performance, however it encounters significant challenges due to its high computational complexity. In order to deal with these challenges, this paper proposes channel estimation employing deep learning with one-dimensional convolutional neural network (1D CNN) schemes to enhance conventional least squares (LS) estimation. The first scheme provides better performance compared to conventional LS estimation. However, it is only suitable for OFDM systems with full pilot symbols, leading to decreased transmission efficiency and high complexity. In order to address those problems, the second scheme develops 1D CNN-based channel estimation employing scattered pilot symbols to enhance transmission efficiency and reduce computational complexity. In comparison to conventional LS estimation and deep learning-based channel estimation with bi-gated recurrent unit (bi-GRU), the performance evaluation demonstrates that the proposed 1D CNN-based schemes simultaneously improve channel estimation performance, transmission efficiency, and reduce computational complexity.
Some of the metrics are blocked by your
consent settings
Adaptive K-Repetition Transmission with Site Diversity Reception for Energy-Efficient Grant-Free URLLC in 5G NR
(2024-01-01)
Dataesatu, Arif
;
Sanada, Kosuke
;
Hatano, Hiroyuki
;
Mori, Kazuo
;
Boonsrimuang, Pisit
The fifth-generation (5G) new radio (NR) standard employs ultra-reliable and low-latency communication (URLLC) to provide real-time wireless interactive capability for the internet of things (IoT) applications. To satisfy the stringent latency and reliability demands of URLLC services, grant-free (GF) transmissions with the K-repetition transmission (K-Rep) have been introduced. However, fading fluctuations can negatively impact signal quality at the base station (BS), leading to an increase in the number of repetitions and raising concerns about interference and energy consumption for IoT user equipment (UE). To overcome these challenges, this paper proposes novel adaptive K-Rep control schemes that employ site diversity reception to enhance signal quality and reduce energy consumption. The performance evaluation demonstrates that the proposed adaptive K-Rep control schemes significantly improve communication reliability and reduce transmission energy consumption compared with the conventional K-Rep scheme, and then satisfy the URLLC requirements while reducing energy consumption.
Some of the metrics are blocked by your
consent settings
Adaptive K-Repetition Transmission Employing Site Diversity Reception for 5G NR Uplink Grant-Free URLLC
(2023-01-01)
Dataesatu, Arif
;
Sanada, Kosuke
;
Hatano, Hiroyuki
;
Mori, Kazuo
;
Boonsrimuang, Pisit
The Internet of Things (IoT) is currently being employed for wireless real-time interactive systems with ultra-reliable and low-latency communications (URLLC) that provide high service quality for the fifth generation (5G) new radio (NR) standard. Grant-free (GF) transmission with K-Repetition (K-Rep) is a transmission technique that aims to meet the URLLC requirements. However, the K-Rep increases the number of packet transmissions, which may cause severe interference and substantial energy consumption. This paper employs site diversity reception to the GF K-Rep scheme and proposes its adaptive control mechanism to decrease the number of repeated transmissions in order to improve communication reliability and energy consumption for IoT URLLC users. According to our simulation results, the proposed site diversity reception for the K-Rep scheme can significantly improve the reliability compared with the conventional K-Rep under single-cell reception. Additionally, the proposed adaptive K-Rep control scheme can reduce the transmission energy consumption greatly, hence saving battery resource of IoT URLLC users.
Some of the metrics are blocked by your
consent settings
System Performance Enhancement with Energy Efficiency Based Sleep Control for 5G Heterogeneous Cellular Networks
(2022-04-01)
Dataesatu, Arif
;
Sanada, Kosuke
;
Hatano, Hiroyuki
;
Mori, Kazuo
;
Boonsrimuang, Pisit
This paper presents an improved sleep control algorithm for small base stations (SBSs) in 5G New Radio (NR) heterogeneous cellular networks (HetNets). HetNets consist of various base station tiers, including macro base stations (MBSs) and small base stations (SBSs), and have been suggested as a promising solution to enhance wireless coverage and network capacity, employing many SBSs into the MBS coverage. However, power consumption increases significantly as a result of an increase in the number of the SBSs. To solve this problem, the SBS sleep control has been proposed to reduce power consumption for the SBSs and improves energy efficiency, whereas it deteriorates system throughput compared with no sleep control system, consequently degrading the quality of service (QoS) performance at user equipments (UEs). This paper proposes an enhanced algorithm for SBS sleep control based on energy efficiency as a decision criterion for SBS operating state. From the evaluation results through computer simulation, the proposed scheme can provide improved performance for both energy efficiency and system throughput simultaneously, that is it can improve energy efficiency while maintaining almost the same system throughput as the no sleep control system. Concretely, the proposed scheme has the 14.89% improvement in energy efficiency while providing almost the same system throughput of over 99%, compared with no sleep control system
Some of the metrics are blocked by your
consent settings
A Deep Learning-Based Channel Estimation for High-Speed Train Environments
(2022-01-01)
Siriwanitpong, Aphitchaya
;
Boonsrimuang, Pornpawit
;
Mori, Kazuo
;
Boonsrimuang, Pisit
A communication system in the railway track environment provides constant channel coefficient property as trains travel on a predetermined route and speed. This channel characteristic provides advantages in designing a channel estimation. This paper proposes a channel estimation algorithm based on a deep learning network called the Convolutional Neural Network (CNN). The CNN has trained with an average Channel Frequency Response (CFR) dataset on railway track environments with different multi-path fading and noises. The CFR can be estimated using a known pilot symbol as conventional methods. The estimated CFR is also used to select the right CFR for multi-path fading compensation. The CNN will then classify the estimated CFR by recognizing estimated channel characteristics and determining the most matched estimated channel for equalization of received signals in a data channel. The simulation results show that the performance of the deep learning algorithms outperforms that of the conventional algorithms. Furthermore, the proposed method delivers better Bit Error Rate (BER) performance since the deep learning-based channel estimation can categorize the features of the channel characteristics with different multi-path and doppler shifts.
Some of the metrics are blocked by your
consent settings
Energy Efficiency Enhancement in 5G Heterogeneous Cellular Networks Using System Throughput Based Sleep Control Scheme
(2020-02-01)
Dataesatu, Arif
;
Boonsrimuang, Pornpawit
;
Mori, Kazuo
;
Boonsrimuang, Pisit
Currently, Cellular architectures are designed with an efficient providing infrastructure is one of the critical challenges in 5G dense heterogeneous cellular networks (HetNets). By adding many small base stations (SBSs) in a macro base station (MBS) is one way to support the rapid growth of mobile data communication, high data rate services and to provide continuous coverage. The high number of network elements leads to a significant increase in power consumption. To solve the problem, the SBS on/off algorithm has been introduced to reduce power consumption but also reduced energy efficiency as we called the conventional schemes. This paper we proposed as the SBS switching to sleep state algorithm based on the system throughput (MBS cell throughput and SBS cell throughput) is used the decision criteria for SBS to be in the sleep state. The simulation results, The proposed scheme can reduce the total power consumption of the network and enhance energy efficiency more than the conventional schemes.
Some of the metrics are blocked by your
consent settings
Low Complexity Equalization Method for ZP-OFDM under Highly Mobile Environments
(2020-02-01)
Tanangsanakool, Saha
;
Reangsuntea, Pongsathorn
;
Mori, Kazuo
;
Boonsrimuang, Pisit
Many Interferences from multipath fading channels in the mobile channels, there are many types of research trying to compensate for such interferences. The Zero-padded OFDM (ZP-OFDM) is a popular method that has much attention as an efficient technique to improve the performances. In the high-speed mobile channel, the Doppler frequency destroyed orthogonality among subcarriers and inter-carrier interference (ICI), It would degrade the bit error rate (BER) performance. We proposed both equalization (TDE) method and CIR estimation with less computation complexity for the ZP-OFDM signal that can solve this problem. The salient feature of our proposed method is using a training sequence (TS) instead of using Zero-padded which enables for estimation of CIR. And we show that the proposed method shows the less computational complexity when compared with the conventional frequency-domain equalization, the proposed TDE method employs an iterative solution instead of using the direct inverse matrix method. We validate the proposed methods presented by computer simulations under highly mobile environments. The simulation results show a comparison of the effectiveness of the proposed TDE method and conventional TDE methods.
Some of the metrics are blocked by your
consent settings
Low-complexity based TDE Method for OFDM signal in higher time-varying fading channels
(2020-01-01)
Tanangsanakool, Saha
;
Reangsuntea, Pongsathorn
;
Mori, Kazuo
;
Boonsrimuang, Pisit
Orthogonal Frequency Division Multiplexing (OFDM) signal would be damaged significantly by inter-carrier interference (ICI) in higher time-varying fading channels. The ICI leads to fatal degradation of bit error rate (BER) performance due to the loss of orthogonality among subcarriers. To solve this problem, this paper proposes a high accuracy time-domain channel impulse response (CIR) estimation method and low-complexity based time-domain equalization (TDE) method for solving the simultaneous equations instead of using an inverse matrix calculation which can achieve better BER performance and lower computation complexity even in higher time-varying fading channels. The salient features of proposed method are to employ a time-domain training sequence (TS) in the estimation of channel impulse response (CIR) instead of using pilot subcarriers in the frequency domain and to employ the time domain equalization (TDE) method with maximum likelihood (ML) estimation instead of using a conventional frequency domain equalization (FDE) method. This paper also proposes a low-complexity iterative method for solving the simultaneous equations instead of using an inverse matrix calculation, which remains the computation complexity up to 7.8% of inverse matrix calculation with the same BER performance but achieves the BER performance when compared with the conventional method. This paper presents various simulation results in higher time-varying fading channels (vehicle speed ≈ 381 km/hrs) to demonstrate the effectiveness of the proposed method as compared with conventional FDE and TDE methods.
Some of the metrics are blocked by your
consent settings
A PAPR Reduction for FBMC-OQAM Signals using ABC-OPTS Scheme
(2019-04-29)
Boontra, Pitchaya
;
Mata, Tanairat
;
Dataesatu, Arif
;
Mori, Kazuo
;
Boonsrimuang, Pisit
Partial Transmit Sequence (PTS) scheme has been applied to the OFDM signal for solving the high PAPR problem which can achieve better PAPR performance. However, because of the structure of the FBMC-OQAM signal which is different from the OFDM signal, the PTS scheme is not suitable for the FBMC-OQAM signal. For this reason, this paper considers the PAPR reduction for FBMC-OQAM signal. This paper proposes an overlapped PTS (OPTS) with Artificial Bee Colony (ABC) algorithm. The silent features are to improve the PAPR by modifying the PTS scheme as OPTS scheme and less computational complexity in the PAPR optimization process by using the ABC algorithm. The PAPR reduction effectiveness of the proposed method has been confirmed by the simulation results in the paper.
Some of the metrics are blocked by your
consent settings
Channel Estimation and Equalization Methods for ZP-OFDM under Highly Mobile Environments
(2019-04-29)
Tanangsanakool, Saha
;
Reangsuntea, Pongsathorn
;
Mori, Kazuo
;
Boonsrimuang, Pisit
Zero-Padded OFDM (ZP-OFDM) has been attracted a lot of attention as an efficient technique to improve the performance in severe multipath fading channels. Many works were devoted to the equalization method for ZP-OFDM in quasi-static channel model. However, an inter-carrier interference (ICI) which occurred under highly mobile environments would be destroyed orthogonality among subcarriers and causes the degradation of bit error rate (BER) performance due to the time domain channel impulse responses (CIRs) are assumed to be constant over one OFDM symbol. The time domain equalization (TDE) method in conjunction with a time domain CIR estimation method is proposed to solve this problem for the ZP-OFDM signal in the time domain. The advantage of the proposed method is to apply a training sequence (TS) instead of using ZP which enables for estimation of CIR. And also to reduce computational complexity, the proposed method is employed time domain equalization based on the minimum mean squared error (MMSE-TDE) instead of using the conventional frequency domain equalization based on MMSE (MMSE-FDE) method. This paper presents various simulation results under highly mobile environments to demonstrate the effectiveness of proposed TDE method as compared with conventional demodulation methods.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results