RESIDUE NUMBER SYSTEMS AND INTELLIGENT MULTI-AGENT TECHNOLOGIES FOR ROBUST AND ADAPTIVE WIRELESS SENSOR NETWORKS

Abstract

 Wireless Sensor Networks (WSNs) have emerged as a pivotal technology for real-time data acquisition in diverse applications, ranging from environmental monitoring to industrial automation. It has been established that the most significant obstacle to  the functionality of WSNs is their vitality, speed, and dependability. WSNs are governed by a finite supply of energy, making it challenging to replace or rejuvenate energy resources. Also, because WSNs are used to get important information from the environment, they need to be fast, reliable, and able to keep working even if they break. Because they have an impact on the lifetime and performance of the network as a whole, it is critical to plan WSNs in a reliable, energy-efficient, and fault-tolerant manner. This paper introduces a novel approach to enhance the efficiency and reliability of WSNs by integrating Residue Number Systems (RNS) and Intelligent Multi-Agent Technologies. The Chinese Remainder Theorem (CRT)-based packet splitting and Low-Energy Adaptive Clustering Hierarchy (LEACH) algorithm were created to cut down on energy use. For the moduli set {2ⁿ⁺¹-1, 2ⁿ, 2ⁿ-1}, a High Spread REverse Converter (HISPREC) was also proposed and implemented on the basis of Mixed Radix Conversion in order to rapidly convert the CH received residues to the original message. Additionally, fault tolerant WSNs using intelligent multi-agent technology to monitor, control and allow the network to continuously operate in the presence of faults, as well as eliminate any faulty node due to power loss. The utilization of Residue Number Systems at the sensor nodes introduces a parallel and energy-efficient computation paradigm. By leveraging the inherent properties of residue arithmetic, the proposed system minimizes power consumption and extends the network's operational lifetime. Furthermore, the integration of Intelligent Multi-Agent Technologies facilitates dynamic and adaptive decision-making processes within the network.