Open AccessMachine learning based for reducing energy conserving in WSN
Author(s) -
Bassam Noori Shaker,
Manar Joundy Hazar,
Esraa Raheem Alzaidi
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1530/1/012100
Subject(s) - wireless sensor network , bottleneck , computer science , network packet , energy consumption , cluster analysis , computer network , key distribution in wireless sensor networks , node (physics) , mobile wireless sensor network , process (computing) , real time computing , wireless , wireless network , engineering , embedded system , artificial intelligence , telecommunications , electrical engineering , structural engineering , operating system
Two main factors pose challenges in designing wireless sensor network systems, namely energy and bandwidth. In this paper, we will focus on the topic of decreasing energy consuming in wireless networks by employing the Artificial intelligent in this domain. In wireless sensor networks (WSNs), the sensors are working by small batteries. Since the small batteries are restricted power resources, they should use carefully. The proposed algorithm extends the life of these batteries by making use of artificial intelligence science in general and cluster technology in particular, by finding the optimal number of clusters for the network so that the routing process consumes the least amount of energy and that is the bottleneck in the energy consumption in the network. The K-mean algorithm used as the basis for the network sensor clustering process and optimal fixed packet size used according to radio parameters and transceiver channel conditions. By following this manner, the energy consumption of each sensor node can be decreased individually then the overall network lifetime will be increased.