Distributed Q-Learning for Aggregated Interference Control in Cognitive Radio Networks

Galindo-Serrano, Ana; Giupponi, Lorenza

doi:10.1109/tvt.2010.2043124

Cited by 203 publications

(136 citation statements)

References 12 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Several solutions can be envisaged to tackle this problem e.g. by reducing the states space through fuzzy RL algorithms [18], or by distributing the learning process using a cooperative multi-agent RL approach [19].…”

Section: Simulation Resultsmentioning

confidence: 99%

Q-Learning for Policy Based SON Management in wireless Access Networks

Daher

Jemaa

Decreusefond

2017

2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)

View full text Add to dashboard Cite

Abstract-Self organized networks has been one of the first concrete implementations of autonomic network management concept. Currently, several Self-Organizing-Network (SON) functions are developed by Radio Access Network (RAN) vendors and already deployed in many networks all around the world. These functions have been designed independently to replace different operational tasks. The concern of making these functions work together in a coherent manner has been studied later in particular in SEMAFOUR project where a Policy Based SON Management (PBSM) framework has been proposed to holistically manage a SON enabled network, namely a network with several individual SON functions. Enriching this PBSM framework with cognition capability is the next step towards the realization of the initial promise of SON concept: a unique self-managed network that responds autonomously and efficiently to the operator high level requirements and objectives. This paper proposes a cognitive PBSM system that enhances the SON management decisions by learning from past experience using Q-learning approach. Our approach is evaluated by simulation on a SON enabled Long-Term Evolution Advanced (LTE-A) network with several SON functions. The paper shows that the decisions are enhanced during the learning process and discusses the implementation options of this solution.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Q-Learning for Policy Based SON Management in wireless Access Networks

Daher

Jemaa

Decreusefond

2017

2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)

View full text Add to dashboard Cite

show abstract

“…This approach requires user-specific utility parameters which cannot always be acquired in many situations [4]. The authors in [14] integrated a Q-learning method with an ANN. However, both RL and ANN suffer from the same aforementioned less generalization problem; moreover, ANNs slow calculation rate at run-time, local minima, and over-fitting problems are some of the additional limitations.…”

Section: Rrm and Icic Related Workmentioning

confidence: 99%

Impact of Learning Algorithms on Random Neural Network based Optimization for LTE-UL Systems

Adeel

Larijani

Javed

et al. 2015

NPA

View full text Add to dashboard Cite

This paper presents a context-aware decision making solution to the problem of radio resource management (RRM) and inter-cell interference coordination (ICIC) in long-term evolution-uplink (LTE-UL) system. The limitations of existing analytical, artificial intelligence (AI), and machine learning (ML) based approaches are highlighted and a novel integration of random neural network (RNN) based learning with genetic algorithm (GA) based reasoning is presented. Initially, three learning algorithms (gradient descent (GD), adaptive inertia weight particle swarm optimization (AIW-PSO), and differential evolution (DE)) are applied to RNN and two learning algorithms (GD and levenberg-marquardt (LM)) are applied to artificial neural network (ANN). In the second phase, the GA based reasoning is applied to the trained ANN and RNN models for performance optimization. Finally, the ANN and RNN based optimization results are compared with the state-of-the-art fractional power control (FPC) schemes in terms of user throughput and power consumption. The simulation results revealed that an RNN-DE based cognitive engine (CE) can provide up to 14% more cell capacity along with 6dBm and 9dBm less user power consumption as compared to RNN-GD and FPC methods respectively.

show abstract

“…Despite its limitations, the independent Q-learning approach has been widely adopted in the cognitive radio literature. In some cases (e.g., [36]), the issues related to convergence are acknowledged and simulation results are presented to show that the agents achieve an equilibrium. In other cases (e.g., [37]), the question of convergence is not discussed.…”

Section: B Reinforcement-learning Techniquesmentioning

confidence: 99%

Learning and Reasoning in Cognitive Radio Networks

Gavrilovska

Atanasovski

Macaluso

et al. 2013

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Abstract-Cognitive radio networks challenge the traditional wireless networking paradigm by introducing concepts firmly stemmed into the Artificial Intelligence (AI) field, i.e., learning and reasoning. This fosters optimal resource usage and management allowing a plethora of potential applications such as secondary spectrum access, cognitive wireless backbones, cognitive machine-to-machine etc. The majority of overview works in the field of cognitive radio networks deal with the notions of observation and adaptations, which are not a distinguished cognitive radio networking aspect. Therefore, this paper provides insight into the mechanisms for obtaining and inferring knowledge that clearly set apart the cognitive radio networks from other wireless solutions.

show abstract

Distributed Q-Learning for Aggregated Interference Control in Cognitive Radio Networks

Cited by 203 publications

References 12 publications

Q-Learning for Policy Based SON Management in wireless Access Networks

Q-Learning for Policy Based SON Management in wireless Access Networks

Impact of Learning Algorithms on Random Neural Network based Optimization for LTE-UL Systems

Learning and Reasoning in Cognitive Radio Networks

Contact Info

Product

Resources

About