Topology Control of Wireless Sensor Networks by Radio Transmit Power Adjustment Based on Learning Automata

learning automata

Table of Contents


In networks with network topology control infrastructure, this is an issue that arises when designing a network, but in wireless sensor networks for a variety of reasons, including their case nature, the lack of a specific infrastructure, and the network’s ongoing topological changes(learning automata). It becomes a matter of running time and after network design. In most cases, the initial arrangement of the sensor nodes in this type of network is random and cannot guarantee the construction of a suitable topology that can provide uniform and complete coverage for the network environment.

On the other hand, in order to maintain a continuous topological structure for the network that can guarantee the complete coverage of the network as well as the continuity of network performance, the number of nodes scattered at the network level is generally several times the required number.

learning automata
Wireless sensors networks

This will significantly increase the amount of energy loss due to overactive and unnecessary activation of the sensor nodes, as well as the radio interference of the nodes and the overlap of the sensory area of ​​the network nodes. Adjusting the radio transmitting power of the network nodes One of the most efficient methods of topology control in wireless sensor networks is discussed in this dissertation.

It should be noted that the energy consumption of nodes and their radio interference in wireless sensor networks, in turn, are two very challenging issues in these networks that have attracted the attention of scientists and researchers in this field for many years. And. The approaches proposed to solve these two problems are generally based on reducing the radio transmittance power of nodes and thus reducing the interference of radio transmissions as well as reducing the energy consumption in nodes.


The reason for using learning automata as a possible learning tool to solve this problem is as follows:

Learning automata work well in situations where no information is available. Learning automata perform well in situations where there is uncertainty.

  1. Learning automata to feed feedback at each stage to improve their situation they need a simple environment
  2. Learning automata are very useful as a model for learning in distributed environments and multiple transactions with limited communication and incomplete information.
  3. Learning automata have a simple structure and therefore can be easily implemented in software or hardware.
  4. These automated machines have very low computational loads and are therefore easily usable in real-time applications.
  5. Learning automata can be well-used in applications that are complex and unsafe, do not have a mathematical model, or can be used with distributed control and modeling applications by a set of autonomous agents.

Considering the above-mentioned features about the learning atoms and the characteristics of the sensor networks mentioned below, it can be concluded that the learning automata can be a suitable model for use in the application proposed in this dissertation. It increases the tendency to use algorithms that can be distributed and used locally. This is especially important due to the energy constraints on the sensor nodes and the tendency to reduce the transfer of additional information in order to prevent energy loss. Studies to date have shown that learning atoms in such distributed environments show good performance. Limited resources, especially energy, in such networks. The pay network increases. This learning automates are a good choice for their simple structure and the very simple amplification signal they receive from their surroundings.

The computational overhead of these learning atoms is very low. In addition, since the packages sent by each node in these networks can be received by all the neighbors in that node, the required amplification signals can only be included in these packets by adding a small overhead. This will prevent the transfer of any additional packages. The intensity of the topological changes in the sensor networks will make the activity environment of these networks dynamic and unpredictable. In such dynamic environments, the use of adaptive algorithms that can adapt to changing environmental conditions and maintain their efficiency is strongly felt. Due to the fact that these learning atoms have the ability to adapt to changes in the environment or in other words work well in dynamic environments, they can be used to solve various problems in these networks.

The occurrence of interference in radio communications is also uncertain. This uncertainty necessitates the design of algorithms and mechanisms in these networks that have the ability to operate in such an environment with the least amount of information. Given that the amplification signal received by Atamata is a random variable learner whose instantaneous value does not provide any information about the relative efficiency of Atamata in the long run, the existence of defects and delays in the received information based on the received model is a significant effect.

Automata will not learn from all the above. It can be concluded that by accurately adjusting the radio transmission power of sensor nodes, in addition to reducing power consumption and energy loss in wireless sensor networks and radio interference nodes, topology connectivity and full network coverage Can be guaranteed. In this dissertation, we try to provide a topology control algorithm based on adjusting the radio transmitting power of nodes in wireless sensor networks, relying on the capabilities of automatic learning in solving problems mentioned in the previous section.

Topology Control of Wireless Sensor Networks by Radio Transmit power adjustment

About KSRA

The Kavian Scientific Research Association (KSRA) is a non-profit research organization with the goal of providing research / educational services in December 2013. The members of the community had formed a virtual group on the Vibes social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.

KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.

Our main services Based on Education for all spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.

The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.


+ posts

Maryam kakaei was born in 1984 in Arak. She holds a Master's degree in Software Engineering from Azad University of Arak.

Website | + posts

Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.

Website | + posts

Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.