An efficient neural network LEACH protocol to extended lifetime of wireless sensor networks

Area of Science:

• Computer Science
• Electrical Engineering
• Network Engineering

Background:

• Wireless Sensor Networks (WSNs) face significant energy depletion challenges, limiting their operational lifespan.
• Traditional routing protocols like LEACH and ILEACH struggle with energy holes and inefficient cluster head selection.
• Optimizing energy efficiency is crucial for the sustained performance and reliability of WSNs.

Purpose of the Study:

• To introduce NN_ILEACH, a novel neural network-based routing protocol for WSNs.
• To enhance network longevity and energy efficiency by addressing energy depletion issues.
• To improve overall network performance metrics such as throughput and packet delivery ratio.

Main Methods:

• Developed NN_ILEACH, integrating a neural network for cluster head selection with the Energy Hole Removing Mechanism (EHORM).
• Conducted extensive simulations to compare NN_ILEACH against traditional protocols (LEACH, ILEACH).
• Evaluated performance based on network lifetime, throughput, packet delivery ratio, and energy consumption.

Main Results:

• NN_ILEACH extended network lifetime to 11,361 rounds, a >20-fold improvement over LEACH's 505 rounds.
• Achieved a 30% increase in throughput and a 25% enhancement in packet delivery ratio.
• Reduced overall energy consumption by 40% compared to existing protocols.

Conclusions:

• NN_ILEACH significantly outperforms traditional protocols in WSNs, demonstrating superior energy efficiency and network longevity.
• The protocol's enhancements in throughput and packet delivery ratio highlight its effectiveness in dynamic environments.
• NN_ILEACH offers a promising foundation for developing more resilient and sustainable IoT systems through advanced routing strategies.