Location Updating Scheme of Sink Node Based on Topology Balance and Reinforcement Learning in WSN

Wang, Xindi; Zhou, Qingfeng; Qu, Chunxiao; Gao, Chen; Xia, Junjuan

doi:10.1109/access.2019.2929756

Cited by 9 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reinforcement learning (RL) algorithm calculates a potential and effective path to the base station and then integrates the node to achieve the optimal path 9 . Multiuser multiarmed bandit (UM‐MAB) concept collects data based on the virtual head (VH) energy efficiency.…”

Section: Literature Surveymentioning

confidence: 99%

Design of efficient location‐based multipath self‐adaptive balancer router using particle swarm optimization in wireless sensor network

Sakthivel¹,

Manikandan²,

Vivekanandhan³

2022

Int J Communication

View full text Add to dashboard Cite

Summary The power sensor terminals control in wireless sensor network (WSN) communicate within a small number of its radio range. As a branch operating based on the cluster routing protocol, it has proven to be effective in network topology management, energy reduction, and path connection link quality of the path. Location‐based clusters are categorized into member nodes and group/cluster heads (CHs). The CH election process increases the overhead of the network. The processing and energy limitations of the nodes are considered for the CH election process. The allocation of system resources is the major issue in the area of networks. In this work, the proposed multipath self‐adaptive balancer routing‐based particle swarm optimization (MLBAR‐PSO) achieves load balancing by means of the link quality of the route and the calculated average latency and reliability of the path. In this way, different trust values are set in each category. The forwarding node value is the value of each node based on the weight value, which is calculated based on the energy ratio of the node and the distance between the hiding node and the target node. Particle swarm optimization (PSO) selects the head cluster from a specific location within the cluster to enable other nodes to interact with the CH without spending energy. Also, the algorithm is used to find the optimal path for the base station and significantly increases the energy to reduce the distance and delay over the lifetime of the network.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Design of efficient location‐based multipath self‐adaptive balancer router using particle swarm optimization in wireless sensor network

Sakthivel¹,

Manikandan²,

Vivekanandhan³

2022

Int J Communication

View full text Add to dashboard Cite

show abstract

“…In terms of the time complexity of the proposed RL solutions, [70] proposes a constant time approach since the size of the set of tasks and the number of the neighbor nodes are fixed at initialization. But most of the other proposed algorithms, such as [54,72,79,95,101], require a quadratic time complexity with an execution time that increases exponentially as the size of the state and/or the action space increases. The authors in [76] try to decrease the Computational complexity by combining the hidden layer nodes which have similar functions.…”

Section: Cachingmentioning

confidence: 99%

“…Wang et al [95] have addressed the problem caused by 817 scaling-up in WSNs and propose a location update scheme of 818 the mobile sink node to achieve more efficient network topology. First, the sink node updates its location by collecting information from certain key nodes and searches for the best performing location to define it as the final location.…”

mentioning

confidence: 99%