-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we propose an intelligent hybrid automatic repeat request (iHARQ) scheme for high-speed downlink packet access (HSDPA) systems. The challenge in the hybrid automatic repeat request (HARQ) control problem of HSDPA is how to choose an appropriate modulation and coding scheme (MCS) for initial transmission in the situation wherein the channel quality indication (CQI) has report delay. The iHARQ scheme will determine the suitable MCS to maximize the system throughput and guarantee the block error rate requirement in such an uncertain environment. By modeling the HARQ behavior as a Markov decision process, we adopt fuzzy logics to determine an appropriate MCS for each initial packet transmission. In addition, a Q-learning algorithm is utilized to update the fuzzy rule base, according to well-designed reinforcement signals fed back from the HSDPA system, such that the iHARQ scheme can adapt to the delayed CQI. Simulation results show that, compared with a conventional adaptive threshold selection method, the proposed iHARQ scheme increases the system throughput by up to 75.2%.
IEEE Transactions on Vehicular Technology 06/2011; · 1.92 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Generally, optimization techniques for resource allocation of orthogonal frequency-division multiple-access (OFDMA) systems are infeasible for real-time applications. In this paper, with consideration of grouping for subscriber stations (SSs), a resource-allocation scheme by an optimization technique of a genetic algorithm is proposed for the uplinks of IEEE 802.16 OFDMA systems. The genetic algorithm with SS grouping resource-allocation (GGRA) scheme first designs a rate assignment strategy that is applied with a predefined residual lifetime to dynamically allocate resource to each service. It then aggregates high-correlation SSs into the same group, where the SSs will be allocated to different slots to avoid mutual user interference. Finally, the GGRA scheme finds an optimal assignment matrix for the system by the genetic algorithm based on the SS groups to greatly lessen the computation complexity. The GGRA scheme can also maximize the system throughput and fulfill the quality-of-service (QoS) requirements. Simulation results show that the proposed GGRA scheme performs better than the efficient and fair scheduling (EFS) algorithm and the maximum largest weighted delay first (MLWDF) algorithm in system throughputs, voice/video packet drop rates, unsatisfied ratios of hypertext transfer protocol (HTTP) users/packets, and file transfer protocol (FTP) throughputs. The computation complexity of the GGRA scheme is also tractable and, thus, feasible for real-time applications.
IEEE Transactions on Vehicular Technology 04/2010; · 1.92 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a dynamic priority resource-allocation (DPRA) scheme is proposed for uplinks in IEEE 802.16 wireless communication systems. The DPRA scheme dynamically gives priority values to four types of service traffic based on their urgency degrees and allocates system radio resources according to their priority values. It can maximize the system throughput and satisfy differentiated quality-of-service (QoS) requirements. Furthermore, the DPRA scheme performs consistent allocation for packets of users to conform to the uplink frame structure of IEEE 802.16, to fulfill the QoS requirement, and to reduce the computational complexity. Simulation results show that the proposed DPRA scheme performs very close to the optimal method, which is by exhaustive search in system throughput, and it outperforms the conventional efficient and fair scheduling (EFS) algorithm in the performance measures such as system throughput, real-time polling service (rtPS) packet dropping rate, ratio of unsatisfied non-real-time polling service (nrtPS), and average transmission rate of the best effort (BE) service. In addition, the DPRA scheme takes only 1/1000 and 1/10 the computational times of the optimal method and the conventional EFS algorithm, respectively, thus making it more feasible for real applications.
IEEE Transactions on Vehicular Technology 11/2009; · 1.92 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a fuzzy Q-learning-based hybrid automatic repeat request (FQL-HARQ) scheme is proposed to enhance the system performance of high speed downlink packet access (HSDPA) in universal mobile telecommunications system (UMTS). In the HSDPA system, it is an important issue to choose modulation and coding scheme (MCS) for new data packet when channel quality indicator (CQI) is inaccurate. Hence, the purpose of the FQL-HARQ scheme is to determine a suitable MCS for new data packet so as to maximize the system throughput while guarantee the block error rate (BLER) requirement. In the FQL-HARQ scheme, the fuzzy logic is used to choose a suitable MCS for each new data packet. According to the feedback information from the HSDPA system, the Q-learning algorithm is adopted to update fuzzy rule base. This makes the FQL-HARQ scheme can adapt to the variation of environment. Simulation results show that the proposed scheme can increase the system throughput of up to 70% compared to the conventional adaptive method in the case with CQI report delay.
Vehicular Technology Conference Fall (VTC 2009-Fall), 2009 IEEE 70th; 10/2009
-
[show abstract]
[hide abstract]
ABSTRACT: The use of ldquocognitive radiordquo (CR) technology is viewed as the key technology to fully utilize the bandwidth. In this paper, a CR-based dynamic spectrum access (DSA) device named fuzzy active period adaptor (FAPA) is proposed in a downlink transmission of IEEE 802.16h systems. FAPA decides the active period of IEEE 802.16h system to efficiently coexist with a WLAN system in unlicensed spectrum. Simulation results show that the fuzzy active period adaptation improve the overall throughput, and reduce the idle time of the spectrum.
Communications and Networking in China, 2009. ChinaCOM 2009. Fourth International Conference on; 09/2009
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a dynamic priority-based resource allocation (DPRA) scheme is proposed for uplinks in IEEE 802.16 wireless communication systems. The goal of the DPRA scheme is to maximize the system throughput while satisfying diverse QoS requirements. Four types of multimedia traffic are considered, where these multimedia traffic are given urgency degrees via dynamic priority values, and the radio resources are allocated according to their priority values. Also the DPRA scheme performs consistent allocation for packets with multimedia traffic in aspects of subchannel, modulation order, and power. Simulation results show that the proposed DPRA scheme outperforms the conventional algorithm in system throughput by an amount of 15%. The rtPS packet dropping rate of DPRA scheme is 70% lower than other schemes and satisfies QoS requirements. Besides, the proposed DPRA scheme can achieve less computational complexity and lower transmission overhead.
Vehicular Technology Conference, 2008. VTC 2008-Fall. IEEE 68th; 10/2008
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we propose a QoS-promoted dynamic bandwidth allocation (Q-DBA) method to support quality-of-service (QoS) requirement services for Ethernet passive optical networks (EPON). The Q-DBA method classifies the three types of services: voice, video, and data into six priorities. It can not only satisfy QoS requirements of real-time service and but also improve the QoS of non-real-time packets. Simulation results show that the Q-DBA can fulfill the video dropping probability requirement while the conventional dynamic bandwidth allocation with multiple services (DBAM) fails. Also, the Q-DBA can achieve the fairness index of average data delay close to 1 but DBAMpsilas fairness index of average data delay varies greatly.
Communications and Networking in China, 2008. ChinaCom 2008. Third International Conference on; 09/2008
-
[show abstract]
[hide abstract]
ABSTRACT: A centralized QoS guaranteed throughput enhancement (QoS GTE) scheduling scheme for downlink relay-assisted WiMAX networks is proposed. The QoSGTE consists of a transmission time based path selection algorithm (TTPSA), a service order based resource allocation algorithm (SO RAA), and a transmission concurrency decision algorithm (TCDA). The TT_PSA selects the path with the minimal transmission time for packets, which takes path loss, shadow fading, and interference into consideration. The SO RAA gives high priority to urgent users and maximizes throughput under QoS satisfaction. The TCDA carries out flexible resource reuse by deciding which relay station (RS) can transmit concurrently using the same frequency and time slots. Simulation results show that the proposed QoSGTE outperforms the scheme of without relay by an amount of 63% and that of the LMP by an amount of 28%, in the system throughput. The QoS GTE can also guarantee QoS requirements of real time services by 97%.
Communications, 2008. ICC '08. IEEE International Conference on; 06/2008
-
[show abstract]
[hide abstract]
ABSTRACT: This paper proposes an adaptive radio resource allocation (ARRA) algorithm for downlink OFDMA/SDMA systems with multimedia traffic. Considering multiple service classes and diverse QoS requirements of multimedia traffic, the ARRA algorithm is designed with the goal to maximize spectrum efficiency and to fulfill quality of service (QoS) requirements. It is composed of two parts, a dynamic priority adjustment (DPA) scheme and a priority-based greedy (PBG) scheme. The DPA adopts a type of time-to-expiration to indicate the degree of user's urgency, and dynamically gives high priorities to urgent users. The PBG allocates the radio resource iteratively, based on a cost value, to maximize the system throughput while allocating enough resource to high-priority users. Simulation results show that the ARRA algorithm outperforms conventional algorithms in terms of system throughput and satisfaction extent of QoS requirements; it can sustain users' QoS requirements up till a traffic load of 0.8, while the conventional algorithms cannot guarantee QoS requirements after a traffic load of 0.3.
IEEE Transactions on Wireless Communications 06/2008; · 2.59 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: WCDMA/WLAN interworking networks are considered to support high-data-rate multimedia services and high mobility. In this paper, we propose a utility function-based access selection method (UFAS) to determine which cell is most suitable for a mobile node's service request in heterogeneous WCDMA and WLAN networks. The UFAS method contains three parts, cells classification, utility function computation, and target cell determination. This utility function is composed of four evaluation functions, and is designed with a balancing index which can reduce the utility value of a cell if the cell is heavily loaded. Simulation results show that the UFAS method achieves larger system throughput than a policy-enabled (PE) handoff decision method (Wang, 1999). Moreover, the UFAS method can reduce handoff occurrence rates and strike a balance between system utilization and cell loading while maintaining QoS requirements.
Personal, Indoor and Mobile Radio Communications, 2007. PIMRC 2007. IEEE 18th International Symposium on; 10/2007
-
[show abstract]
[hide abstract]
ABSTRACT: The paper proposes an adaptive radio resource allocation (ARRA) algorithm for downlink OFDMA/SDMA systems with goals to achieve quality of service (QoS) satisfied and throughput maximized. The ARRA algorithm considers multiple service classes of multimedia traffic and their diverse QoS requirements. It contains two parts, a dynamic priority adjustment scheme and a priority-based greedy (PBG) algorithm. The dynamic priority adjustment scheme gives high priority to urgent users and dynamically adjust the value frame by frame based on users' QoS requirement and queue occupancy. The PBG algorithm allocates the radio resource iteratively according to a cost value to maximize the system throughput while allocating enough resource to high-priority users. Simulation results show that the ARRA algorithm outperforms the conventional algorithms in terms of system throughput under the satisfaction of QoS requirements.
Communications, 2007. ICC '07. IEEE International Conference on; 07/2007
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a Q-learning-based hybrid automatic repeat request (Q-HARQ) scheme is proposed to achieve efficient resource utilization for high speed downlink packet access (HSDPA) in universal mobile telecommunications system (UMTS). The hybrid ARQ procedure is modeled as a discrete-time Markov decision process (MDP), where the transmission cost is defined in terms of the signal-to-interference-and-noise (SINR) which is based on the desired (quality-of-service) QoS parameters of transport block error rate (BLER) for enhancing spectrum utilization subject to QoS constraint. The Q-learning reinforcement algorithm is employed to accurately estimate the transmission cost to perform the most suitable decision of modulation and coding scheme for the packet initial transmission while the requirement of transport block error rate is guaranteed. Simulation results show that the QoS requirement of block error rate for Q-HARQ is nearly met around a reasonable value indeed. In addition, the system throughput of the Q-HARQ can be improved under the specific QoS constraint of BLER. It is verified finally that the Q-HARQ scheme is feasible in the practical system because of the short processing and convergence time.
Vehicular Technology Conference, 2007. VTC2007-Spring. IEEE 65th; 05/2007
-
[show abstract]
[hide abstract]
ABSTRACT: This paper proposes a novel situation-aware data access manager using fuzzy Q-learning technique (FQ-SDAM) for multi-cell WCDMA systems. The FQ-SDAM contains a fuzzy Q-learning-based residual capacity estimator (FQ-RCE) and a data rate scheduler (DRS). The FQ-RCE can accurately estimate the situation-dependent residual system capacity, and appropriately chooses the received interference powers from the home-cell and adjacent-cell as input linguistic variables, which simplifies the multi-cell environment into a single-cell environment by applying a perceptual coordination mechanism. The DRS can effectively allocate the resource for non-real-time terminals by modifying the exponential rule (S. Shakkottai and A.L. Stolyar, 2001), which considers the effect of interference on adjacent cells. Simulation results show that, compared to the link and interference-based demand assignment (LIDA) scheme proposed in S. Kumar and S. Nanda (1999), FQ-SDAM can effectively reduce the packet error probability and improve aggregate throughput of the non-real-time services in both the homogeneous and non-homogeneous multi-cell WCDMA environments. Additionally, the modified exponential rule achieves better system performance than the original exponential rule
IEEE Transactions on Wireless Communications 10/2006; · 2.59 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: A Q-learning-based multirate transmission control scheme (Q-MRTC) for radio resource control (RRC) in WCDMA systems is proposed. The RRC problem is modelled as a semi-Markov decision process (SMDP). We successfully apply a real-time reinforcement learning algorithm, named Q-learning, to accurately estimate the transmission cost for the multi-rate transmission control. For the cost function approximation, we apply the feature extraction method to map the original state space into a more compact set which represents the resultant interference profile. Simulation results show that the Q-MRTC can achieve higher system throughput and better users' satisfaction index, by an amount of 87% and 50%, respectively, than the interference-based multi-rate transmission control scheme, while keeping the QoS requirement.
Personal, Indoor and Mobile Radio Communications, 2002. The 13th IEEE International Symposium on; 10/2002
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a Q-learning-based multirate transmission control scheme (Q-MRTC) for radio resource control (RRC) in WCDMA systems is proposed. The RRC problem is modelled as a semi-Markov de- cision process (SMDP). And we successfully apply a real-time reinforcement learning algorithm, named Qlearning, to accurately estimate the transmission cost for the multi-rate transmission control. For the cost function approximation, we apply the feature extraction method to map the original state space into a more compact set which represents the resultat mteferece profile. Simulation results show that the Q-MRTC can achieve higher system throughput and better users' satisfaction index, by an amount of 87% and 50%, respectively, than the interference-based multi-rate transntission control scheme, while keeping the QoS requirement. Keyword: multi-rate transmission, radio resource management, Q-learning, and CDMA communication system.
09/2002;
-
[show abstract]
[hide abstract]
ABSTRACT: The paper proposes congestion control using fuzzy/neural
techniques for integrated voice and data direct-sequence code division
multiple access/frame reservation multiple access (DS-CDMA/FRMA)
cellular networks. The fuzzy/neural congestion controller is constituted
by a pipeline recurrent neural network (PRNN) interference predictor, a
fuzzy performance indicator, and a fuzzy/neural access probability
controller. It regulates the traffic input to the integrated voice and
data DS-CDMA/FRMA cellular system by determining proper access
probabilities for users so that congestion can be avoided and the
throughput can be maximized. Simulation results show that the
DS-CDMA/FRMA fuzzy/neural congestion controllers perform better than
conventional DS-CDMA/PRMA with channel access function in terms of voice
packet dropping ratio, corruption ratio, and utilization. In addition,
the neural congestion controller outperforms the fuzzy congestion
controller
IEEE Journal on Selected Areas in Communications 03/2000; · 3.41 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We propose intelligent call admission control for wideband CDMA
cellular systems to support differentiated QoS requirements. The
intelligent call admission controller (ICAC) adopts fuzzy and neural
network techniques to make admission decision for a new call request by
considering the QoS measures of all service types, predicted next-step
existing-call interference, and estimated new-call interference. It
contains a fuzzy call admission processor, a pipeline recurrent neutral
network (PRNN) interference predictor and a fuzzy equivalent
interference estimator. Simulation results indicate that ICAC attains
better performance in keeping QoS guaranteed, blocking probability and
admitted number of users. Furthermore, ICAC is more adaptive and stable
than SIR-based CAC in wideband CDMA cellular systems
Vehicular Technology Conference, 2000. IEEE VTS-Fall VTC 2000. 52nd; 02/2000
-
IEEE Journal on Selected Areas in Communications. 01/2000; 18:283-293.
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, an intelligent transmission controller (ITC) with
multi-QoS medium access control (MAC) algorithm for TDMA/PRMA wireless
multimedia communication systems is studied. A mini-slot technique is
adopted in the proposed MAC protocol for reducing contention cost, and
these mini-slots are further partitioned into multiple MAC regions where
various MAC regions are for access requests coming from different QoS
(quality-of-service)-class users with their respective access
probabilities. Meanwhile, ITC is designed to adaptively adjust these MAC
regions and access probabilities to enhance the MAC efficiency under QoS
constraints. ITC mainly contains a neural/fuzzy transmission controller
which has PRNN (pipeline recurrent neural network) traffic predictors, a
fuzzy MAC threshold estimator, and a fuzzy access controller. Simulation
results show that the proposed multi-QoS MAC algorithm with ITC can
guarantee QoS requirement and has less data packet delay and higher
achievable system utilization, compared to previous PRMA, IPRMA and FRMA
protocols
Vehicular Technology Conference, 1999. VTC 1999 - Fall. IEEE VTS 50th; 02/1999
-
[show abstract]
[hide abstract]
ABSTRACT: A neural-net based fuzzy connection admission controller for a
wireless ATM network is designed. It is a QoS-guaranteed controller,
where QoSs of both the air interface and ATM network are taken into
consideration. Hence, for the neural fuzzy admission decision
controller, we further design a fuzzy capacity requirement estimator,
fuzzy air interface performance estimator, and a fuzzy system status
estimator for reflecting the equivalent capacity required by the new
call request, air interface performance, and the ATM network status,
respectively. The simulation result shows that the neural fuzzy
connection admission controller can gain high bandwidth utilization for
wireless ATM networks
Vehicular Technology Conference, 1997, IEEE 47th; 06/1997
