Development of Energy Efficient Clustering Protocol in Wireless Sensor Network Using Neuro-Fuzzy Approach

Area of Science:

• Computer Science
• Electrical Engineering
• Network Engineering

Background:

• Wireless sensor networks (WSNs) face significant energy consumption challenges due to limited node power.
• Extending the operational lifetime of WSNs is critical and requires energy-aware protocols.
• Existing clustering protocols often do not adequately address energy efficiency for mobile nodes.

Purpose of the Study:

• To propose a novel neuro-fuzzy energy aware clustering scheme (NFEACS) for WSNs.
• To optimize cluster formation and cluster head selection for improved energy efficiency.
• To enhance the overall network lifetime of wireless sensor networks.

Main Methods:

• Developed a hybrid neuro-fuzzy system combining fuzzy logic and neural networks.
• Utilized a neural network for training based on node energy and received signal strength to estimate cluster head energy.
• Employed fuzzy rules for efficient cluster formation, considering node mobility.

Main Results:

• The proposed NFEACS effectively forms optimum and energy-aware clusters.
• Achieved significant energy efficiency in cluster and cluster head selection.
• Demonstrated superior performance compared to existing clustering schemes in experimental evaluations.

Conclusions:

• NFEACS provides an effective solution for energy-aware clustering in WSNs.
• The scheme successfully balances energy consumption and network lifetime.
• NFEACS is a promising protocol for WSNs, especially those with mobile nodes.