Learning based mechanisms for interference mitigation in self-organized femtocell networks

Nazir, Mohsin; Bennis, Mehdi; Ghaboosi, Kaveh; MacKenzie, Allen B.

doi:10.1109/acssc.2010.5757866

Cited by 36 publications

(30 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [5], two mechanisms for interference mitigation were introduced to support the coexistence of a macrocell network underlaid with self-organized femtocell networks. In one mechanism, the RL approach is used because information exchange among femtocells is not possible and hence each femtocell adapts its strategy and gradually learns by interacting with its environment.…”

Section: Introductionmentioning

confidence: 99%

Base Station Selection in M2M Communication Using Q-Learning Algorithm in LTE-A Networks

Mohammed

Khwaja

Anpalagan

et al. 2015

2015 IEEE 29th International Conference on Advanced Information Networking and Applications

View full text Add to dashboard Cite

A major problem faced by machine type communication (MTC) devices in machine to machine (M2M) communication is the congestion and traffic overloading when incorporating into LTE Advanced networks. In this paper, we present an approach to tackle this problem by providing an efficient way for multiple access in the network and minimizing network overload. We consider the random access network (RAN) between the LTE base stations and MTC devices in the cell. We propose an unsupervised learning algorithm, based on Q-learning, as a means of base station selection scheme where MTC devices continuously adapt to changing network traffic and decide which base station is to be selected on the basis of QoS parameters. Simulation results demonstrate that the proposed algorithm helps MTC devices achieve better performance and, therefore, enhances the M2M communication performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Base Station Selection in M2M Communication Using Q-Learning Algorithm in LTE-A Networks

Mohammed

Khwaja

Anpalagan

et al. 2015

2015 IEEE 29th International Conference on Advanced Information Networking and Applications

View full text Add to dashboard Cite

show abstract

“…Recently, many researchers have proposed algorithms for distributed interference management (see, e.g., [10], [11]). In [11], a Q-learning approach for self-organizing femtocell networks with no information exchange among users was considered.…”

Section: Related Workmentioning

confidence: 99%

“…In [11], a Q-learning approach for self-organizing femtocell networks with no information exchange among users was considered. But provided with situation of dense network users, requirement of maintaining a Q-table to make decision have a slower convergence time.…”

Section: Related Workmentioning

confidence: 99%

Best-Response Distributed Subchannel Selection for Minimizing Interference in Femtocell Networks}

Shah¹

2015

Proceedings of the 1st International Conference on Industrial Networks and Intelligent Systems

View full text Add to dashboard Cite

Abstract-We study the problem of channel selection of noncooperative OFDMA femtocells in two-tiered macro-femto networks. Using a physical channel model, we consider a distributed channel allocation of femtocells and a total capacity objective, which is the total capacity of uplink macro users and femto users. We assume a time-slotted system, a time-invariant channel model (no fading), each user knows the signal-to-interferenceplus-noise ratio (SINR) of all channels, and the channel selection happens only at the beginning of each time-slot. We study the performance of a best-response strategy where each user chooses to transmit in the highest-SINR channel. For simplicity, we focus on the homogeneous 3-link, 2-channel case and show that if all users update their actions every time-slot (i.e., all users make simultaneous moves), an oscillation can occur and result in the worst performance. To avoid the oscillation and achieve the highest total capacity, while still assuming no coordination among the users, we propose a stochastic best-response algorithm, where each user updates its channel selection with a selection probability p. We use a Markov chain to analyze the average capacity performance and use simulation results to confirm our analysis and also provide performance of other homogeneous cases with more number of homogeneous links and channels. It is shown that the highest total capacity can be achieved when the selection probability p is very small. This stochastic best response with small p in effect provides a sequential move mechanism which requires no coordination among the users and hence avoids the oscillation problem from the simultaneous moves.

show abstract

“…where, PL E stands for the transmission loss of electromagnetic signals based on the fundamental modes in the straight roadway; PL roughness stands for the loss caused by the roughness of the roadway wall; P tilt stands for the loss caused by the materials on the roadway wall; PL C stands for the transmission loss of the electromagnetic signals based on the fundamental modes in the bended roadway [3][4][5][6].…”

Section: Electromagnetic Wave Transmission Modelmentioning

confidence: 99%

Underground Coal Mine Positioning System Based on RSSI Positioning Algorithm Improved Through the BP Learning Training

Chen¹

2015

TOEFJ

View full text Add to dashboard Cite

Abstract:The influence of the coal mine geographic environment on the electromagnetic transmission might result in the difficulty of wireless positioning under the mine. Concerning that the influence of the underground working face on the wireless signal attenuation is mainly reflected through the electricity path attenuated and based on the underground geographic differences, two corresponding electromagnetic loss models are established. Under the conditions of low energy consumption and no need for hardware devices, RISS algorithm is found suitable to be used in the underground coal mine. However, the problems of large error and poor precision still exist. This paper first introduces the standard deviation threshold, TSA, as decided by the practical environment; then compares it with the standard deviation, RSA, obtained by the calculation of every target node to finally obtain the modified value of RSS. Based on that, the BP algorithm is introduced for learning training, improvement of the positioning error rate and the system's positioning precision.

show abstract

Learning based mechanisms for interference mitigation in self-organized femtocell networks

Cited by 36 publications

References 13 publications

Base Station Selection in M2M Communication Using Q-Learning Algorithm in LTE-A Networks

Base Station Selection in M2M Communication Using Q-Learning Algorithm in LTE-A Networks

Best-Response Distributed Subchannel Selection for Minimizing Interference in Femtocell Networks}

Underground Coal Mine Positioning System Based on RSSI Positioning Algorithm Improved Through the BP Learning Training

Contact Info

Product

Resources

About