Faulty node detection and recovery scheme for large‐scale wireless sensor network using hosted cuckoo optimization algorithm

Abstract

Summary Large‐scale wireless sensor networks (LS‐WSNs) are used for collecting and monitoring the physical state of the environment. These networks are first sending information to the base station and then the recipient. LS‐WSNs consist of several components, such as battery, sensor, transmitter, receiver and microcontroller circuits. If any one of these hardware components does not work properly, then the entire system will become faulty condition, resulting reducing network life and accuracy. To overcome these hardware node faults, this manuscript proposes an effective deep reinforcement learning (DRL)‐adopted faulty node detection and recovery scheme (FND‐RS) integrated with the hosted cuckoo‐based optimal routing scheme for LS‐WSNs. Here, the DRL process is utilized for noticing and recovering the hardware node fault on sensor. The major objective of this system is ‘to enhance the network life with least energy consumption and also enhance the accuracy of Large Scale Wireless Sensor Networks using hosted cuckoo optimization (HO‐COA) algorithms’. The simulation is done in MATLAB. The experimental results shows that the proposed method attains lower overhead 15.65%, energy loss 21.62%, average packet delivery ratio 13.13%, energy efficiency 23.25%, network lifetime 19.12%, throughput 13.5%, time complexity 19.35% and lower delay 17.55% when compared to the existing methods, like FND‐RS for LS‐WSN in distributed intermittent fault diagnosis algorithm (NDR‐WSN‐DISFD), FND‐RS for LS‐WSN in harmony search algorithm (FNDR‐WSN‐HAS), FND‐RS for LS‐WSN in t‐distribution‐based satin bowerbird optimization (FNDR‐WSN‐t‐DSBO), FND‐RS for LS‐WSN in optimal emperor penguin optimization (FNDR‐WSN‐OEPO) and FND‐RS for LS‐WSN in particle swarm optimization algorithm (FNDR‐WSN‐PSO) respectively.

Application of intelligent algorithm in wireless sensor network node deployment optimization

“…For example, in a wireless sensor network, there may be such a scene: there is a node area in a certain corner of the city, there are many objects around, there are some sensor nodes need to sense these objects, but some sensor nodes do not know what objects in the surrounding area, can not sense these objects. If we consider multiple objective functions at the same time, see Table 1 for details [1][2][3] . 1 and other multi-objective function indicators is independent, so we can regard these independent objective functions as a multi-objective programming problem.…”

Distributed Intermittent Fault Diagnosis in Wireless Sensor Network Using Likelihood Ratio Test

“…An effective deep reinforcement learning for faulty node detection and recovery schemes in large WSNs is given in [4]. The method is integrated with the hosted cuckoo-based optimal routing scheme and enhances the network life with least energy utilization.…”

“…Malfunction in hardware may happen due to a problem in sensing unity, power unity, location unity and processing unit. On the other hand software failure may happen because of problems in sensor programs [4]. Problems in the transceiver, improper estimation of channel states may cause communication failures in the sensor network.…”

Intelligent collection system of human resource information based on clustering algorithm

“…Its advantage is that the algorithm has high performance, because its time complexity is 0, where n is all the data, h is the number of clusters, t is the number of iterations of the algorithm (t <n) and the geometric properties of the data all affect the process of the K-means algorithm. Selection of the initial value optimization algorithm, Bradley optimization algorithm, Lichuan genetic algorithm , proposed many optimization algorithms, such as combining antivirus with K-means optimization, o re algorithm, etc [1][2].…”

“…In the process of clustering data, the most critical point is to calculate the distance of data objects. Among them, the smaller the distance, the greater the similarity, on the contrary, the smaller the similarity [3].…”