Browsing by Author "Ren, FC"

Now showing 1 - 9 of 9

A neural-net based fuzzy connection admission controller for wireless ATM
(1997)
Chen, YS
;
Chang, CJ
;
Tzou, WY
;
Ren, FC
;
交大名義發表
A neural-net based fuzzy connection admission controller for a wireless ATM network is designed in this paper. it is a QoS-guaranteed controller, where QoSs of both air interface and ATM network are taken into consideration. Hence, for the neural fuzzy admission decision controller, we further design fuzzy capacity requirement estimator, fuzzy air interface performance estimator, and 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.
A Q-learning-based multi-rate transmission control scheme for RRC in WCDMA systems
(2002-01-01)
Ren, FC
;
Chang, CJ
;
Chen, YS
;
交大工研院聯合研發中心
;
NCTU/ITRI Joint Research Center
In this paper, a Q-learning-based multi-rate 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). And 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.
Centralized and distributed down-link power control methods for a DS/CDMA cellular mobile radio system
(1997-02-01)
Chang, CJ
;
Ren, FC
;
電信工程研究所
;
電信研究中心
;
Institute of Communications Engineering
For down-link communication in a DS/CDMA cellular mobile radio system, the transmitted power of the base station must be effectively adjusted in real-time Fashion to achieve good communication quality because the system exists multipath short-term fading and near-far problem. In this paper, we propose two down-link power control mechanisms: one is the centralized SIR-balancing method and the other is the distributed SIR-based method. We investigate how the outage probability is affected by system parameters and optimally design the parameters for these two down-link power control mechanisms. Also, the two down-link power control mechanisms are compared and discussed.
Design of power control mechanisms with PCM realization for the uplink of a DS-CDMA cellular mobile radio system
(1996-08-01)
Chang, CJ
;
Lee, JH
;
Ren, FC
;
電信工程研究所
;
電信研究中心
Power control (PC) is an important issue in a direct sequence-code division multiple access (DS-CDMA) cellular mobile radio system. Higher link performance and greater system capacity cannot be achieved unless an appropriate PC mechanism is employed. In previous research, a delta-modulation (DM) realization of strength-based and SIR-based PC mechanisms for uplink communication has been studied by simulation. In order to obtain higher PC trackability, in this paper we study a pulse-code-modulation (PCM) realization of the above two PC mechanisms for the uplink of a DS-CDMA cellular mobile radio system. The simulation results presented here indicate that PC mechanisms with PCM realization for the uplink can achieve a lower outage probability and thus higher link performance than PC mechanisms with DM realization. We also obtain optimal design parameters such as the stepsize and the control mode for the two PCM PC mechanisms. In addition, we compare the two PCM PC mechanisms in terms of their outage probability and stability and find that the strength-based mechanism has a higher outage probability but greater stability than the SIR-based mechanism.
Design of power control mechanisms with PCM realization for the uplink of a DS-CDMA cellular mobile radio system
(1996-08-01)
Chang, CJ
;
Lee, JH
;
Ren, FC
;
電信工程研究所
;
電信研究中心
Power control (PC) is an important issue in a direct sequence-code division multiple access (DS-CDMA) cellular mobile radio system. Higher link performance and greater system capacity cannot be achieved unless an appropriate PC mechanism is employed. In previous research, a delta-modulation (DM) realization of strength-based and SIR-based PC mechanisms for uplink communication has been studied by simulation. In order to obtain higher PC trackability, in this paper we study a pulse-code-modulation (PCM) realization of the above two PC mechanisms for the uplink of a DS-CDMA cellular mobile radio system. The simulation results presented here indicate that PC mechanisms with PCM realization for the uplink can achieve a lower outage probability and thus higher link performance than PC mechanisms with DM realization. We also obtain optimal design parameters such as the stepsize and the control mode for the two PCM PC mechanisms. In addition, we compare the two PCM PC mechanisms in terms of their outage probability and stability and find that the strength-based mechanism has a higher outage probability but greater stability than the SIR-based mechanism.
Fuzzy/neural congestion control for integrated voice and data DS-CDMA/FRMA cellular networks
(2000-02-01)
Chang, CJ
;
Chen, BW
;
Liu, TY
;
Ren, FC
;
電信工程研究所
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 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 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 voice packet dropping ratio, corruption ratio, and utilization. In addition, the neural congestion controller outperforms the fuzzy congestion controller.
Intelligent call admission control for differentiated QoS provisioning in wideband CDMA cellular systems
(2000)
Chang, CJ
;
Shen, S
;
Lin, JH
;
Ren, FC
;
電信工程研究所
In this paper, 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 neural 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.
Q-learning-based multirate transmission control scheme for RRM in multimedia WCDMA systems
(2004-01-01)
Chen, YS
;
Chang, CJ
;
Ren, FC
;
交大名義發表
;
National Chiao Tung University
In this paper, a Q-learning-based multirate transmission control (Q-MRTC) scheme for radio resource management in multimedia wide-band code-division multiple access. (WCDMA) communication systems is proposed. The multirate transmission control problem is modeled as a Markov decision process where the transmission cost is defined in terms of the quality-of-service (QoS) parameters for enhancing spectrum utilization subject to QoS constraint. We adopt a real-time reinforcement learning algorithm, called Q-learning, to accurately estimate the transmission cost for the MRTC. In the meantime,we successfully employ the feature extraction method and radial basis function network (RBFN) for the Q-function that maps the original state space into a feature vector that represents the resultant interference profile. The state space and memory-storage requirement are then reduced and the convergence property of the Q-learning algorithm is improved. Simulation results show that the Q-MRTC for a multimedia WCDMA system can achieve higher system throughput by an amount of 80% and better users' satisfaction than the interference-based MRTC scheme, while the QoS requirements are guaranteed. Also, compared to the table-lookup method, the storage requirement is reduced by 41%.
QoS-guaranteed fuzzy transmission controller for dynamic TDMA protocol in multimedia communication systems
(2002-10-01)
Ren, FC
;
Chang, CJ
;
Cheng, RG
;
電信工程研究所
;
Institute of Communications Engineering
The paper proposes a QoS-guaranteed fuzzy transmission controller (FTC) for the dynamic TDMA protocol in multimedia communication systems. The dynamic TDMA protocol adopts a mini-slot technique for reducing contention cost, and the mini-slots are further partitioned into multiple MAC regions that users can access with their respective quality-of-service (QoS) requirements. The FTC mainly contains a Sugeno self-tuning fuzzy MAC threshold controller and a fuzzy access controller. The former applies a position-gradient-type reasoning method to properly determine the MAC regions; the latter employs max-min inference fuzzy logic to determine the access probabilities of users for enhancing dynamic TDMA efficiency under the QoS constraint. Simulation results show that the dynamic TDMA protocol with FTC can always guarantee the QoS requirement of real-time packet loss probability, regardless of the non-real-time traffic loads. Furthermore, it achieves higher system utilisation and less non-real-time packet delay compared to previously proposed PRMA, IPRMA and FRMA protocols.