A Survey of Using Swarm Intelligence Algorithms in IoT

Sun, Weifeng; Tang, Min; Zhang, Lijun; Huo, Zhiqiang; Shu, Lei

doi:10.3390/s20051420

Cited by 96 publications

(46 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this context, swarm intelligence algorithms aim to control drone swarms in what concerns their behaviors based on two approaches namely optimization and consensus. This article aims to analyze optimization approaches such as PSO, ACO, and BCO [ 9 ], as well as consensus approaches mainly Paxos and Raft algorithms [ 79 ].…”

Section: System Componentsmentioning

confidence: 99%

“…PSO proposed by Kennedy and Eberhart in 1995 is inspired by the flocking behavior of birds [ 9 ]. PSO can be used to allow drones to cooperate in searching for the best solution to solve an identified problem, such as avoiding an obstacle.…”

Section: System Componentsmentioning

confidence: 99%

“…The ACO algorithm is devised to assist in finding optimal paths based on the travelling behavior of ants in search for food sources while releasing pheromones on their paths [ 9 ]. As ants pursue food sources, the release of more pheromones on a path is a likely indication of a food source.…”

Section: System Componentsmentioning

confidence: 99%

“…In a swarm, each drone acts as a simple agent in a networked control system. All such agents are conjoined in a multi-agent system to work based on the integration of a networking system and a computational system aiming to allow simple behaviors to be distributed across all agents (drones), giving rise to collaborative behaviors capable of solving complex problems [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Drone Swarms as Networked Control Systems by Integration of Networking and Computing

Asaamoning

Mendes

Rosário

et al. 2021

Sensors

View full text Add to dashboard Cite

The study of multi-agent systems such as drone swarms has been intensified due to their cooperative behavior. Nonetheless, automating the control of a swarm is challenging as each drone operates under fluctuating wireless, networking and environment constraints. To tackle these challenges, we consider drone swarms as Networked Control Systems (NCS), where the control of the overall system is done enclosed within a wireless communication network. This is based on a tight interconnection between the networking and computational systems, aiming to efficiently support the basic control functionality, namely data collection and exchanging, decision-making, and the distribution of actuation commands. Based on a literature analysis, we do not find revision papers about design of drone swarms as NCS. In this review, we introduce an overview of how to develop self-organized drone swarms as NCS via the integration of a networking system and a computational system. In this sense, we describe the properties of the proposed components of a drone swarm as an NCS in terms of networking and computational systems. We also analyze their integration to increase the performance of a drone swarm. Finally, we identify a potential design choice, and a set of open research challenges for the integration of network and computing in a drone swarm as an NCS.

show abstract

Section: System Componentsmentioning

confidence: 99%

Section: System Componentsmentioning

confidence: 99%

Section: System Componentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Drone Swarms as Networked Control Systems by Integration of Networking and Computing

Asaamoning

Mendes

Rosário

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Also, two parameters -the optimum cost c and the width parameter g -have to be appropriately specified. In this study, these two hyper-parameters in the SVM model are fine-tuned using the Particle Swarm Optimization (PSO) method based on the training data sets [38]. The PSO is a population-based heuristic method that optimizes a problem using swarm intelligence.…”

Section: B Fault Diagnosis Analysis Based On Original Vibration Signalsmentioning

confidence: 99%

Adaptive Multiscale Weighted Permutation Entropy for Rolling Bearing Fault Diagnosis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Fault diagnosis of rolling bearing is of great importance to ensure high reliability and safety in the industrial machinery system. Entropy measures are useful non-linear indicators for time series complexity analysis and have been widely applied in bearing fault diagnosis in the past decade. In this paper, an improved entropy measure is proposed, named Adaptive Multiscale Weighted Permutation Entropy (AMWPE). Then, a new rolling bearing fault diagnosis method is developed based on the AMWPE and multi-class SVM. For comparison, an experimental bearing dataset is analyzed using the AMWPE and conventional entropy measures, and then multi-class SVM is adopted for fault type classification. Further, the robustness of different entropy measures against noise is studied by analyzing noisy signals with various Signal-to-Noise Ratios (SNRs). The experimental results have demonstrated the effectiveness of the proposed method in bearing fault diagnosis under different fault types, severity degrees, and SNR levels. INDEX TERMS Fault diagnosis, rolling bearing, entropy measure, support vector machine. YU ZHANG received the B.Eng. degree from the

show abstract