Fuzzy Reinforcement Learning for Routing in Wireless Sensor Networks

Martyna, Jerzy

doi:10.1007/3-540-34783-6_61

Cited by 4 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually in the works reported online learning or structure and knowledge adaptation, intelligent agents run autonomously on each node, collect packets from the data stream and exchange information through light-weight messages. Unsupervised learning is carried out using Reinforcement Learning (RL) [18], Fuzzy Neural Networks [10] or Self-organizing Maps (SOM). The most often used RL in MANETs attempts to find a policy that maps states of the world to the actions the agent ought to take in those states.…”

Section: Related Workmentioning

confidence: 99%

Evolving Fuzzy Modeling for MANETs Using Lightweight Online Unsupervised Learning

Lekova

2010

Int J Wireless Inf Networks

View full text Add to dashboard Cite

The study presents a methodology for evolving fuzzy modeling tasks in Mobile Ad hoc Networks (MANETs) based on distributed data-driven fuzzy clustering and reasoning. The fuzzy clustering is exploited for the purpose of learning fuzzy inference rules online. That calls for one-pass Lightweight Evolving Fuzzy Clustering Method (LEFCM) suitable for deploying on mobile devices with constrained resources in MANETs. There is no standard method to determine the optimal number of fuzzy rules and most of the fuzzy systems still apply the trial and error method, unsuitable for online modeling tasks. The proposed methodology addresses the issues of uncertainties, simplicity and speed to run in non-intrusive way. It estimates online the number of clusters and their centers in the input data space, accordingly the fuzzy rules, by online adaptation of the LEFCM threshold value that affects the number of clusters. Adaptation is based on the combination of geometrical and statistical analyses, as well as on incorporating a multidimensional fuzzy membership degree into the clustering process. The proposed LEFCM is proven by using traditional cluster validity indexes and tested on real data sets.

show abstract

Section: Related Workmentioning

confidence: 99%

Evolving Fuzzy Modeling for MANETs Using Lightweight Online Unsupervised Learning

Lekova

2010

Int J Wireless Inf Networks

View full text Add to dashboard Cite

show abstract

“…The simulation results look very promising for the authors. A fuzzy scheme of routing for sensor networks was proposed [12]. A fuzzy-scheme for filtering routing decisions was proposed [13].…”

Section: Related Workmentioning

confidence: 99%

A Secure and Energy-Efficient Scheme for Group-Based Routing in Heterogeneous Ad Hoc Sensor Networks and Its Simulation Analysis

et al. 2008

View full text Add to dashboard Cite

We present Fuzzy Group-Based Routing Algorithm (FGRA), a secure, energy-efficient scheme for routing in sensor networks. In this scheme, we consider the formation of multipaths for routing. Using fuzzy logic for generating decisions of forwarding or withholding packets, we show that our scheme is robust, efficient and scalable for a large number of nodes. In our scheme, routing takes place with the help of groups of nodes, which includes situations when the nodes are disconnected. We incorporate security in the design of our routing algorithm by using a mobile-agents-based approach. Our scheme is data-centric where named data packets are considered as the focal point of the system, and in this way it can be adapted for any application. We perform some simulations in NS2, and demonstrate that our scheme shows good performance results with scope for additional research.

show abstract

“…Although, these literature reveal a great insight into distributed learning, and in specific to distributed inference in energy and bandwidth challenged environment, very few directed research have implemented reinforcement learning in sensor networks. The application of reinforcement learning specific to sensor networks have only been researched mostly for routing information from sensors back to a base-station [68][69]. [70] gives basic concepts of learning theory approach in sensor networks based on several specific sensor network applications.…”

Section: Dynamic Power Managementmentioning

confidence: 99%

Hierarchical Aggregation and Intelligent Monitoring and Control in Fault-Tolerant Wireless Sensor Networks

Sridhar

Madni

Jamshidi

2007

IEEE Systems Journal

View full text Add to dashboard Cite

The primary idea behind deploying sensor networks is to utilize the distributed sensing capability provided by tiny, low powered and low cost devices. Multiple sensing devices can be used cooperatively and collaboratively to capture events or monitor space more effectively than a single sensing device. The realm of applications envisioned for sensor networks is diverse including military, aerospace, industrial, commercial, environmental and health monitoring. Typical examples include: traffic monitoring of vehicles, crossborder infiltration-detection and assessment, military reconnaissance and surveillance, target tracking, habitat monitoring and structure monitoring, to name a few. Most of the applications envisioned with sensor networks demand highly reliable, accurate and fault-tolerant data acquisition process. The integrity of data alone can have tremendous effects on the performance of any data acquisition system. Due to the low manufacturing cost, the sensors lend themselves to be deployed in large numbers with a high spatial distribution. Such a large deployment scheme often generates enormous amount of data that needs to be efficiently summarized and delivered for analysis and ix TABLE OF CONTENTS LIST OF FIGURES .

show abstract

Fuzzy Reinforcement Learning for Routing in Wireless Sensor Networks

Cited by 4 publications

References 7 publications

Evolving Fuzzy Modeling for MANETs Using Lightweight Online Unsupervised Learning

Evolving Fuzzy Modeling for MANETs Using Lightweight Online Unsupervised Learning

A Secure and Energy-Efficient Scheme for Group-Based Routing in Heterogeneous Ad Hoc Sensor Networks and Its Simulation Analysis

Hierarchical Aggregation and Intelligent Monitoring and Control in Fault-Tolerant Wireless Sensor Networks

Contact Info

Product

Resources

About