English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Unmanned aerial vehicles (UAVs) have emerged as a promising candidatesolution for data collection of large-scale wireless sensor networks (WSNs). Inthis paper, we investigate a UAV-aided WSN, where cluster heads (CHs) receivedata from their member nodes, and a UAV is dispatched to collect data from CHsalong the planned trajectory. We aim to minimize the total energy consumptionof the UAV-WSN system in a complete round of data collection. Toward this end,we formulate the energy consumption minimization problem as a constrainedcombinatorial optimization problem by jointly selecting CHs from nodes withinclusters and planning the UAV's visiting order to the selected CHs. Theformulated energy consumption minimization problem is NP-hard, and hence, hardto solve optimally. In order to tackle this challenge, we propose a novel deepreinforcement learning (DRL) technique, pointer network-A* (Ptr-A*), which canefficiently learn from experiences the UAV trajectory policy for minimizing theenergy consumption. The UAV's start point and the WSN with a set ofpre-determined clusters are fed into the Ptr-A*, and the Ptr-A* outputs a groupof CHs and the visiting order to these CHs, i.e., the UAV's trajectory. Theparameters of the Ptr-A* are trained on small-scale clusters problem instancesfor faster training by using the actor-critic algorithm in an unsupervisedmanner. At inference, three search strategies are also proposed to improve thequality of solutions. Simulation results show that the trained models based on20-clusters and 40-clusters have a good generalization ability to solve theUAV's trajectory planning problem in WSNs with different numbers of clusters,without the need to retrain the models. Furthermore, the results show that ourproposed DRL algorithm outperforms two baseline techniques.

UAV Trajectory Planning in Wireless Sensor Networks for Energy Consumption Minimization by Deep Reinforcement Learning