PSO-Based Sparse Source Location in Large-Scale Environments With a UAV Swarm

Zhang, Junqi; Lu, Yehao; Wang, Cheng; Wang, Cheng; Zang, Di; Abusorrah, Abdullah; Zhou, MengChu

doi:10.1109/tits.2023.3237570

Cited by 18 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its combination with recent deep learning methods [69][70][71][72][73] should be investigated to handle large-scale processes and systems [74][75][76][77][78][79][80][81][82][83][84]. Additionally, we are interested in considering the application of IDJaya to practical scenarios, i.e., industrial robots [39][40][41], automatic guided vehicle (AGV) [85,86], autonomous driving [87], resource scheduling [88,89] and multi-agent systems [77,[90][91][92][93].…”

Section: Discussionmentioning

confidence: 99%

An Improved Discrete Jaya Algorithm for Shortest Path Problems in Transportation-Related Processes

et al. 2023

Self Cite

View full text Add to dashboard Cite

Shortest path problems are encountered in many engineering applications, e.g., intelligent transportation, robot path planning, and smart logistics. The environmental changes as sensed and transmitted via the Internet of Things make the shortest path change frequently, thus posing ever-increasing difficulty for traditional methods to meet the real-time requirements of many applications. Therefore, developing more efficient solutions has become particularly important. This paper presents an improved discrete Jaya algorithm (IDJaya) to solve the shortest path problem. A local search operation is applied to expand the scope of solution exploration and improve solution quality. The time complexity of IDJaya is analyzed. Experiments are carried out on seven real road networks and dense graphs in transportation-related processes. IDJaya is compared with the Dijkstra and ant colony optimization (ACO) algorithms. The results verify the superiority of the IDJaya over its peers. It can thus be well utilized to meet real-time application requirements.

show abstract

Section: Discussionmentioning

confidence: 99%

An Improved Discrete Jaya Algorithm for Shortest Path Problems in Transportation-Related Processes

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, reference [21] proposed a memetic algorithm based on isomorphic transcoding space to optimize the deployment of UAVs, especially to solve the problem of UAV distribution in energy-efficient artificial intelligence of things data collection. Reference [22] addresses the use of height information of UAVs for multi-source localization in the efficiency problem, a sound source localization model compatible with PSO is proposed. Reference [23] considers UAV-enabled wireless powered communication networks scenarios where UAVs need to cover ground-based wireless devices, a non-dominated sequential genetic algorithm with improved K-means initialization and variable dimensionality mechanism is proposed to solve the power and trajectory optimization problem for UAVs.…”

Section: Related Studiesmentioning

confidence: 99%

A PSO-based energy-efficient data collection optimization algorithm for UAV mission planning

Lin,

Wang,

Tian

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

With the development of the Internet of Things (IoT), the use of UAV-based data collection systems has become a very popular research topic. This paper focuses on the energy consumption problem of this system. Genetic algorithms and swarm algorithms are effective approaches for solving this problem. However, optimizing UAV energy consumption remains a challenging task due to the inherent characteristics of these algorithms, which make it difficult to achieve the optimum solution. In this paper, a novel particle swarm optimization (PSO) algorithm called Double Self-Limiting PSO (DSLPSO) is proposed to minimize the energy consumption of the unmanned aerial vehicle (UAV). DSLPSO refers to the operational principle of PSO and incorporates two new mechanisms. The first mechanism is to restrict the particle movement, improving the local search capability of the algorithm. The second mechanism dynamically adjusts the search range, which improves the algorithm’s global search capability. DSLPSO employs a variable population strategy that treats the entire population as a single mission plan for the UAV and dynamically adjusts the number of stopping points. In addition, the proposed algorithm was also simulated using public and random datasets. The effectiveness of the proposed DSLPSO and the two new mechanisms has been verified through experiments. The DSLPSO algorithm can effectively improve the lifetime of the UAV, and the two newly proposed mechanisms have potential for optimization work.

show abstract