KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 17

Some of the metrics are blocked by your
consent settings
Deep Learning Based Power Allocation Schemes for NOMA System with Imperfect SIC
(2023-01-01)
Saetan, Worawit
;
Thipchaksurat, Sakchai
Non-orthogonal multiple access (NOMA) has been a promising technology for 5G communication system. NOMA allows more than one user to utilize the same resource at the same time, which can lead to high performance in terms of spectral efficiency, energy efficiency or fairness. NOMA enables power domain multiplexing and separates the multiplexed signal by using successive interference cancellation (SIC). Therefore, the full benefit of NOMA depends on power allocation. However, in practical system, residual interference caused by SIC process can severely degrade a system performance. In this paper, we propose two power allocation schemes based on deep learning to alleviate the effect of imperfect SIC for downlink NOMA system, including a deep learning-based sum rate power allocation scheme (DL-SRPAS) and a deep learning-based energy-efficient power allocation scheme (DL-EEPAS). our two proposed schemes learn two optimal power allocation schemes provided through exhaustive search. We search the solution of the optimization problems, where two optimization problems are formulated to maximize the sum rate and the energy efficiency subject to a minimum user data rate requirement. The simulation results verify that our two proposed schemes can alleviate the effect of imperfect SIC and outperform two conventional power allocation schemes which maximize the sum rate and the energy efficiency without considering imperfect SIC. In addition, our proposed schemes achieve near-optimal performance with very low computational time.
Some of the metrics are blocked by your
consent settings
Location Prediction of Rogue Access Point Based on Deep Neural Network Approach
(2022-01-01)
Ketkhaw, Apisak
;
Thipchaksurat, Sakchai
One of the serious security problems in wireless local networks (WLAN) is the existence of the rogue access points (RAPs). To prevent our network from the RAP attacks, we need to identify the RAPs by using the RAP detection methods. However, the identification of RAP location is also a challenging task. The objective of this paper is to propose the location prediction scheme for the RAP.We call our proposed scheme as the location prediction of rogue access point (LPRAP). The LPRAP scheme consists of two mechanisms, the RAP detection mechanism and the RAP location prediction mechanism. We apply the concept of the fingerprint in the RAP detection mechanism by considering the SSID, time duration of broadcasting beacon frame and MAC address. We show that this mechanism can detect the number of RAP. For the RAP location prediction mechanism, we utilize the deep neuron network (DNN) to predict the location of RAPs and evaluate its effectiveness. We evaluate the performance of LPRAP by comparing with those of other machine learning methods such as Support Vector Machine (SVM), KNearest Neighbor (KNN), Naive Bayes, and Multi-layer Perceptron (MLP). We also compare with particle swarm optimization algorithm. The results show that LPRAP can accurately predict the location of RAP up to 99.29%.
Some of the metrics are blocked by your
consent settings
Application of Deep Learning to Fairness-Based Power Allocation for 5G NOMA System with Imperfect SIC
(2020-01-01)
Saetan, Worawit
;
Thipchaksurat, Sakchai
Non-orthogonal multiple access (NOMA) has been a promising technique for 5G communication system, which has higher spectrum efficiency, energy efficiency and fairness than that of orthogonal multiple access (OMA). NOMA serves more than one user by sharing the same time-frequency resource block and uses successive interference cancellation (SIC) to separate multiuser signal. However, the error propagation in the SIC procedure, which is called the imperfect SIC, can cause a severe performance loss. In this paper, we apply the deep learning to power allocation in order to mitigate the impact of imperfect SIC under fairness perspective for downlink NOMA system. Firstly, we formulate an optimization problem aiming to maximize the minimum user rate to provide fairness for all users. Secondly, exhaustive search method is used to solve the formulated problem and thus the optimal power allocation factor is obtained. Lastly, we train the deep neural network to predict the obtained power allocation factor. The simulation results show that our proposed scheme provides the performance close to that provided by exhaustive search. Furthermore, the proposed scheme has much lower complexity than the exhaustive search scheme.
Some of the metrics are blocked by your
consent settings
Power Allocation for Sum Rate Maximization in 5G NOMA System with Imperfect SIC: A Deep Learning Approach
(2019-10-01)
Saetan, Worawit
;
Thipchaksurat, Sakchai
Non-orthogonal multiple access (NOMA) is regarded as a promising technology for enhancing the spectral efficiency (SE) in 5G communication system. In this paper, we propose a power allocation scheme for maximizing sum rate for downlink NOMA system in the presence of imperfect successive interference cancellation (SIC). The proposed scheme uses deep learning to predict the optimal power allocation through exhaustive search. Simulation results reveal that the proposed scheme can achieve the sum rate performance close to the optimal scheme but with much lower computational complexity.
Some of the metrics are blocked by your
consent settings
Application of deep learning to energy-efficient power allocation scheme for 5G SC-NOMA system with imperfect SIC
(2019-07-01)
Saetan, Worawit
;
Thipchaksurat, Sakchai
Non-orthogonal multiple access (NOMA) is a multiuser access technique for 5G communication system, which has drawn more attention from both academia and industry because of its higher spectrum efficiency than that of orthogonal multiple access (OMA). NOMA allows more than one user to access the same time-frequency resource and separates multiuser signal by successive interference cancellation (SIC). However, error propagation in SIC procedure called imperfect SIC can cause a severe performance degradation. In this paper, we propose the application of deep learning to power allocation to reduce the effect of imperfect SIC under energy-efficient perspective for downlink NOMA system. Firstly, we formulate a non-convex optimization problem aiming to maximize energy efficiency subject to a minimum data rate of each user and a total transmit power of base station (BS). Secondly, on the formulated problem, we obtain the optimal power allocation via exhaustive search method. Lastly, we train a deep neural network to predict the obtained power allocation. Simulation results verify that the proposed scheme provides the near optimal performance with very low computational complexity.
Some of the metrics are blocked by your
consent settings
Rogue access point detection mechanism considering sequence number of beacon frame for wireless local area networks
(2017-11-03)
Ketkhaw, Apisak
;
Thipchaksurat, Sakchai
Rogue Access Point (RAP) is one of the serious problem concerned with the security issues. The attacker usually inserts the RAP by setting the information such as Service set identifier (SSID), MAC Address and beacon frame size same as those of the legitimate AP. In this paper, we propose the mechanism for RAP Detection by considering sequence number of beacon frame in wireless local area networks (WLAN). Our proposed mechanism considers sequence number of beacon frame by introducing checking detection window technique for detecting the RAP. We show the effectiveness of mechanism by conducting an experiment. The results show the our proposed mechanism is able to detect RAP accurately.
Some of the metrics are blocked by your
consent settings
Location-based routing scheme with adaptive request zone in mobile ad hoc networks
(2013-01-01)
Kirdpipat, Putthiphong
;
Thipchaksurat, Sakchai
Route discovery process is a major mechanism in the most routing protocols in Mobile Ad Hoc Network (MANET). Routing overhead is one of the problems caused by broadcasting the route discovery packet. To reduce the routing overhead, the location-based routing schemes have been proposed. In this paper, we propose our scheme called Location-based Routing scheme with Adaptive Request Zone (LoRAReZ). In LoRAReZ scheme, the size of expected zone is set adaptively depending on the dis-tance between source and destination nodes. Computer simulation has been conducted to show the effectiveness of our propose scheme. We evalu-ate the performances of LoRAReZ scheme in the terms of packet delivery fraction (PDF), routing overhead, average end-to-end delay, throughput, packet collision, average hop count, average route setup time, and power consumption. We compare those performance metrics with those of Lo-cation Aided Routing (LAR) and Location Aware Routing Protocol with Dynamic Adaptation of Request Zone (LARDAR) protocols. The simula-tion results show that LoRAReZ can provide all the better performances among those of LAR and LARDAR schemes. © 2013 The Institute of Electronics, Information and Communication Engineers.
Some of the metrics are blocked by your
consent settings
Impact of mobility on Location-based routing with adaptive request zone in mobile ad hoc networks
(2012-10-02)
Kirdpipat, Putthiphong
;
Thipchaksurat, Sakchai
In this paper, we present the impact of mobility on our scheme called Location-based Routing with Adaptive Request Zone (LoRAReZ). In LoRAReZ, the size of expected zone and request zone are set adaptively based on the distance between the source node and destination node. We evaluate the impact of mobility on the performance of LoRAReZ in terms of packet delivery fraction, routing overhead, end-to-end delay, throughput and power consumption by comparing with those of the traditional Ad Hoc On-Demand Distance Vector (AODV) and Modified Ad Hoc On-Demand Distance Vector (MAODV). The results show that LoRAReZ can provide the better performance than those of AODV and MAODV. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Doppler spread mitigation using harmonic transform for wireless OFDM systems in mobile communications
(2010-01-01)
Saiyod, Saiyan
;
Thipchaksurat, Sakchai
;
Varakulsiripunth, Ruttikorn
In wireless OFDM systems, the system performance is suffered from frequency offset and symbol timing offset due to the Doppler effect. Using the discrete Fourier transform (DFT) and inverse discrete Fourier transform (IDFT) for traditional signal transformation from the time-domain into frequency-domain, and vice versa, the system performance may be severely degraded. To make the OFDM system that can tolerate the above problems, we have considered that the harmonic transform can be applicable to the traditional signal transformation, thereby improving the system performance. In this paper, we combine the good characteristics of harmonic transform and instantaneous frequency to be a novel transformation for wireless OFDM systems. We propose a modified discrete harmonic transform (MDHT) which can be performed adaptively. Our proposed scheme called the modified discrete harmonic transform OFDM (MDHT-OFDM scheme). We derive the equations of the novel discrete harmonic transform which are suitable for wireless OFDM systems and the novel channel estimation cooperated with the novel transformation. The proposed channel estimation is performed in both time-domain and frequency-domain. The performance of a MDHT-OFDM scheme is evaluated by means of a simulation. We compare the performance of a MDHT-OFDM scheme with one of the conventional DFT-OFDM scheme in the term of symbol error rate (SER). MDHT-OFDM scheme can achieve better performance than that of the conventional DFT-OFDM scheme in mitigating the Doppler spread. Copyright © 2010 The Institute of Electronics, Information and Communication Engineers.
Some of the metrics are blocked by your
consent settings
Effect of shadow cluster on predictive user mobility behavior scheme in cellular networks
(2009-12-01)
Intarasothonchun, Silada
;
Thipchaksurat, Sakchai
;
Varakulsiripunth, Ruttikorn
In this paper, we propose a scheme for improved performance of resource reservation and call admission control for cellular networks called Predictive User Mobility Behavior (PUMB) scheme. This algorithm is proposed in which bandwidth is allocated more efficiently to neighboring cells by key mobility parameters in order to provide Quality of Service (QoS) guarantees for transferring traffic. The cell visiting probability (CVP) is used to form the shadow cluster cell, where a mobile unit is likely to visit, by comparing with shadow cluster probability threshold. We are interested in the effect of the shadow cluster probability threshold in PUMB because when shadow cluster probability threshold increases, the MU's shadow cluster size decreases so that the suitable shadow cluster probability threshold can define the suitable shadow cluster size for increasing network performance. The performance of the PUMB is demonstrated by simulation results in terms of new call blocking probability and handoff call dropping probability when new call arrival rate and the shadow cluster threshold are varied. Our results show that when shadow cluster probability threshold increases, CBP of MSODB and PUMB decrease while CDP of both schemes increases in all arrival rates. However, PUMB is better than MSODB under different traffic conditions. © 2009 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results