Dynamic traffic steering based on fuzzy Q-Learning approach in a multi-RAT multi-layer wireless network

Muñoz, Pablo; Laselva, Daniela; Barco, Raquel; Mogensen, Preben

doi:10.1016/j.comnet.2014.06.003

Cited by 16 publications

(22 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, delays are due to the complexity during information collection and cost function calculation. Fuzzy logic and artificial neural networks [11] [12], are widely used in the literature to make handover decisions. The application of these complicated algorithms is necessitated by the complexity of handover decisions and wireless networks dynamic conditions.…”

Section: Related Workmentioning

confidence: 99%

Rank Average for handover decision making in heterogeneous wireless networks

Driouache¹,

Naja²,

Jamali³

2018

ICST Transactions on Mobile Communications and Applications

View full text Add to dashboard Cite

Vertical handover mechanism is an important issue in heterogeneous wireless networks. Continuity of service during handover and QoS are relevant issues to deal with. This paper focuses on vertical handover decision making. It proposes a Rank Average method for the best access network selection. This method is an aggregation of two Multi Attributes Decision Making (MADM) methods: Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and VIse Kriterijumska Optimizacija kompromisno Resenja (VIKOR), together with Shannon entropy-based weights. Entropy is an adequate tool to weigh up the handover criteria in a quiet easy and straightforward way. Rank Average outperforms TOPSIS and VIKOR in terms of throughput, end to end delay, packet loss, and significantly reduces the number of unnecessary handovers related to the ping-pong effects. Performance results are obtained within the scope of MIH through NS3 simulator.

show abstract

Section: Related Workmentioning

confidence: 99%

Rank Average for handover decision making in heterogeneous wireless networks

Driouache¹,

Naja²,

Jamali³

2018

ICST Transactions on Mobile Communications and Applications

View full text Add to dashboard Cite

show abstract

“…Cognition and learning capabilities have been introduced in different aspects of mobile networks including routing, resource management and dynamic channel selection [14], [15]. We use Q-learning in this paper that is a model-free reinforcement learning technique.…”

Section: Related Workmentioning

confidence: 99%

“…In other words, represents significance of the previously recorded reward values on ( ). In the simulation study of this paper, we set = 0.995 and the ten time stamps in Equation (9) similar to the described algorithm in [14].…”

Section:  ( )mentioning

confidence: 99%

Traffic Management in 5G Mobile Networks: Selfish Users and Fair Network

Mahmoodi

Jiang

2016

TNC

View full text Add to dashboard Cite

With increasing in heterogeneity of the mobile and wireless networks, including the use of licensed and unlicensed spectrum, and diversity in types of User Equipment (UEs), managing how traffic flows through network while maintaining high level of users' quality of experience is crucial. In this paper, we present a novel traffic management mechanism that maintains the users' quality of experience as well as guaranteeing fairness among users. This traffic management has two separate elements, one that is located at the UE and one that is located at the cloud-based network controller. While each UE maximizes their utility function, which is modelled based on the QoS parameters, selfishly, at the network side, the attempt is to maximize fairness among all users' flows.

show abstract

“…Fuzzy logic can be used to translate human knowledge into a set of basic rules, representing the mapping of the input to the output in linguistic terms . Different approaches have been used in the literature to create, adapt, or refine rules, when knowledge is not available, such as using neural networks, genetic algorithms, and reinforcement learning (RL) . Q‐learning is an RL that works by learning an action‐value function based on the interactions of an agent with the environment and the immediate reward it receives .…”

Section: Introductionmentioning

confidence: 99%

A hybrid trust model using reinforcement learning and fuzzy logic

Aref

Tran

2017

Computational Intelligence

View full text Add to dashboard Cite

Multiagent systems (MASs) are increasingly popular for modeling distributed environments that are highly complex and dynamic, such as e‐commerce, smart buildings, and smart grids. Typically, agents assumed to be goal driven with limited abilities, which restrains them to working with other agents for accomplishing complex tasks. Trust is considered significant in MASs to make interactions effectively, especially when agents cannot assure that potential partners share the same core beliefs about the system or make accurate statements regarding their competencies and abilities. Due to the imprecise and dynamic nature of trust in MASs, we propose a hybrid trust model that uses fuzzy logic and Q‐learning for trust modeling. as an improvement over Q‐learning‐based trust evaluation. Q‐learning is used to estimate trust on the long term, fuzzy inferences are used to aggregate different trust factors, and suspension is used as a short‐term response to dynamic changes. The performance of the proposed model is evaluated using simulation. Simulation results indicate that the proposed model can help agents select trustworthy partners to interact with. It has a better performance compared to some of the popular trust models in the presence of misbehaving interaction partners.

show abstract

Dynamic traffic steering based on fuzzy Q-Learning approach in a multi-RAT multi-layer wireless network

Cited by 16 publications

References 37 publications

Rank Average for handover decision making in heterogeneous wireless networks

Rank Average for handover decision making in heterogeneous wireless networks

Traffic Management in 5G Mobile Networks: Selfish Users and Fair Network

A hybrid trust model using reinforcement learning and fuzzy logic

Contact Info

Product

Resources

About