Data Aggregation in Wireless Sensor Networks Based on Environmental Similarity: A Learning Automata Approach

Abstract

Sensor networks are established of many inexpensive sensors with limited energy and computational resources and memory. Each node can sense special information, such as the temperature, humidity, pressure and so on and then send them to the central station. One of the major challenges in these networks, is limit energy consumption and one of the ways for reducing energy consumption in wireless sensor networks, is reducing the number of packets that are transmitted in the network. Data Aggregation technique that combines related data together and prevents sending additional packets on the network can be effective in reducing the number of packets sent over the network. In this paper a Data Aggregation method based on learning automata is presented and with identifying sensors that are in the similar area, and produce the same data and enable the sensor nodes periodically avoid sending additional packets on the network, and significantly saves energy and increases the lifetime of the network. Simulation results show the optimal performance of the proposed method.

An Enhanced Distributed Data Aggregation Method in the Internet of Things

“…Learning automata includes two phases: selecting phase, and learning phase. In the selecting phase, based on the environment feedback, decisions are made with regard to the upcoming rounds toward improving the existing status in relation to previous steps [32]. 1) Selecting Phase: All of the sensor nodes have an aggregation label (lbl_indicator) which is initialized to 0 at the beginning.…”

An Enhanced Distributed Data Aggregation Method in the Internet of Things

“…Learning automata includes two phases: selecting phase, and learning phase. In the selecting phase, based on the environment feedback, decisions are made concerning the upcoming rounds toward improving the current status about previous steps [43].…”

Semantic Data Gathering of Physical Entities in Semantic Sensor Networks Using Software Agents

“…Each of these geographic areas is considered a physical entity. In order to identify the geographic areas and sensors deployed in a geographic area, the clustering method is employed based on environmental similarity and cellular learning automata [1]. After running this algorithm, certain geographic areas are classified into geographic regions.…”

“…In this way, data gathering does not take place semantically. In addition, all sensor network nodes are active.2 LA-SleepScheduling method[1]: It is a clustering algorithm based on environmental similarity through cellular automata learning technique. In this work, after clustering, a scheduling algorithm is provided to enable sensor nodes for rotation sensing over the environment.…”