A distributed energy-efficient opportunistic routing accompanied by timeslot allocation in wireless sensor networks

Abstract

Sensed data can be forwarded only in one direction to the base station in one-dimensional queue wireless sensor networks different from mesh structure, so the network lifetime will be shortened if some continuous neighboring nodes have run out of their energy. So designing routing protocols for balancing energy consumption is a challenging problem. However, traditional and existing opportunistic routing protocols for one-dimensional queue wireless sensor network proposed so far have not yet addressed this problem to prolong the network lifetime by introducing sleep mode. In this article, we propose a distributed energy-efficient opportunistic routing algorithm accompanied by timeslot allocation by using specific network topology of one-dimensional queue wireless sensor network. In our new algorithm, clustering and routing tree construction is performed while introducing the optimal relay transmission distance achieved by using opportunistic routing principle, and at the same time, interference-free wake up time is scheduled, which may optimize energy consumption and decrease the number of various control messages as possible to prolong the network lifetime. Furthermore, this improves energy efficiency by introducing the operation mode giving up cluster head role. Simulation results show that the proposed protocol can significantly improve the network performance such as energy consumption and network connectivity, when compared with other existing protocols.

Cooperative Communications Based on Deep Learning Using a Recurrent Neural Network in Wireless Communication Networks

“…Tis section initially covers the basics of deep recurrent networks, such as the simple recurrent neural network (RNN), long short-term memory (LSTM) [26], and gated recurrent unit (GRU) [27], before going into how to use one to develop a channel predictor [28,29]. Te computational complexity and statistics of projected CSI are also examined for these predictors [30][31][32]. Unlike feed-forward neural networks, which have unidirectional input fow, RNNs include recurrent self-connections that allow them to memories previous data and show a signifcant promise in timeseries prediction [33].…”

Enhanced QOS energy-efficient routing algorithm using deep belief neural network in hybrid falcon-improved ACO nature-inspired optimization in wireless sensor networks

“…Despite its broad application, WSN suffers from several common constraints, such as restricted energy sources, processing speed, memory, and transmission bandwidth, as a consequence, sensor network effectiveness concerning QoS as well as network lifespan are degraded [3][4][5][6][7][8][9]. Furthermore, it is prevalently declared that the greatest prominent, for one, the shortcoming of WSNs seems to be the considerably shorter lifespan of its sensor nodes owing to stringent energy limitations.…”