In Wireless Sensor Networks(WSNs),Clustering process is widely utilized for increasing the lifespan with sustained energy stability during data transmission.Several clustering protocols were devised for extending netw...In Wireless Sensor Networks(WSNs),Clustering process is widely utilized for increasing the lifespan with sustained energy stability during data transmission.Several clustering protocols were devised for extending network lifetime,but most of them failed in handling the problem of fixed clustering,static rounds,and inadequate Cluster Head(CH)selection criteria which consumes more energy.In this paper,Stochastic Ranking Improved Teaching-Learning and Adaptive Grasshopper Optimization Algorithm(SRITL-AGOA)-based Clustering Scheme for energy stabilization and extending network lifespan.This SRITL-AGOA selected CH depending on the weightage of factors such as node mobility degree,neighbour's density distance to sink,single-hop or multihop communication and Residual Energy(RE)that directly influences the energy consumption of sensor nodes.In specific,Grasshopper Optimization Algorithm(GOA)is improved through tangent-based nonlinear strategy for enhancing the ability of global optimization.On the other hand,stochastic ranking and violation constraint handling strategies are embedded into Teaching-Learning-based Optimization Algorithm(TLOA)for improving its exploitation tendencies.Then,SR and VCH improved TLOA is embedded into the exploitation phase of AGOA for selecting better CH by maintaining better balance amid exploration and exploitation.Simulation results confirmed that the proposed SRITL-AGOA improved throughput by 21.86%,network stability by 18.94%,load balancing by 16.14%with minimized energy depletion by19.21%,compared to the competitive CH selection approaches.展开更多
工业控制场景下5G-A终端传输时延是确定性网络能力的直接表征之一,时延预测对提高网络确定性至关重要。由于传输时延序列的不稳定性和随机性,单一模型难以准确预测。针对该问题,提出一种基于优化变分模态分解(Variational Mode Decompos...工业控制场景下5G-A终端传输时延是确定性网络能力的直接表征之一,时延预测对提高网络确定性至关重要。由于传输时延序列的不稳定性和随机性,单一模型难以准确预测。针对该问题,提出一种基于优化变分模态分解(Variational Mode Decomposition, VMD)和卷积注意力长短时记忆网络(Convolutional Attention Long Short Term Memory Network, CA-LSTM)的传输时延预测方法。为提高VMD的分解性能,利用相关系数检验法确定时延序列分解的模态数,并利用蝗虫优化寻优分解的惩罚因子和保真度系数;设计CA-LSTM网络,借助卷积滤波器以及注意力机制使得网络具备分辨时延特征重要程度的能力;将各模态预测值重建成一维时延值得到预测结果。实验研究结果表明,优化VDM能够将5G终端传输时延序列有效分解,结合CA-LSTM模型相比于经典LSTM在MSE、RMSE和MAE上分别提升了37.1%、21.3%和23.6%。展开更多
文摘In Wireless Sensor Networks(WSNs),Clustering process is widely utilized for increasing the lifespan with sustained energy stability during data transmission.Several clustering protocols were devised for extending network lifetime,but most of them failed in handling the problem of fixed clustering,static rounds,and inadequate Cluster Head(CH)selection criteria which consumes more energy.In this paper,Stochastic Ranking Improved Teaching-Learning and Adaptive Grasshopper Optimization Algorithm(SRITL-AGOA)-based Clustering Scheme for energy stabilization and extending network lifespan.This SRITL-AGOA selected CH depending on the weightage of factors such as node mobility degree,neighbour's density distance to sink,single-hop or multihop communication and Residual Energy(RE)that directly influences the energy consumption of sensor nodes.In specific,Grasshopper Optimization Algorithm(GOA)is improved through tangent-based nonlinear strategy for enhancing the ability of global optimization.On the other hand,stochastic ranking and violation constraint handling strategies are embedded into Teaching-Learning-based Optimization Algorithm(TLOA)for improving its exploitation tendencies.Then,SR and VCH improved TLOA is embedded into the exploitation phase of AGOA for selecting better CH by maintaining better balance amid exploration and exploitation.Simulation results confirmed that the proposed SRITL-AGOA improved throughput by 21.86%,network stability by 18.94%,load balancing by 16.14%with minimized energy depletion by19.21%,compared to the competitive CH selection approaches.
文摘工业控制场景下5G-A终端传输时延是确定性网络能力的直接表征之一,时延预测对提高网络确定性至关重要。由于传输时延序列的不稳定性和随机性,单一模型难以准确预测。针对该问题,提出一种基于优化变分模态分解(Variational Mode Decomposition, VMD)和卷积注意力长短时记忆网络(Convolutional Attention Long Short Term Memory Network, CA-LSTM)的传输时延预测方法。为提高VMD的分解性能,利用相关系数检验法确定时延序列分解的模态数,并利用蝗虫优化寻优分解的惩罚因子和保真度系数;设计CA-LSTM网络,借助卷积滤波器以及注意力机制使得网络具备分辨时延特征重要程度的能力;将各模态预测值重建成一维时延值得到预测结果。实验研究结果表明,优化VDM能够将5G终端传输时延序列有效分解,结合CA-LSTM模型相比于经典LSTM在MSE、RMSE和MAE上分别提升了37.1%、21.3%和23.6%。
文摘为提高光伏发电功率的预测精度,针对支持向量机回归(Support Vector Regression,SVR)模型的预测结果易受其惩罚系数C、敏感损失函数的最大误差系数ε和核函数g影响的问题,提出一种基于新型智能算法-蝗虫算法优化SVR模型参数的光伏发电功率预测模型。由于光伏发电功率数据存在随机性和间隙性的特征,Multi-Agent和分布式思想被引入蝗虫算法优化SVR模型,通过将云计算的MapReduce框架和GOA-SVR结合,提出一种基于MapReduce和GOA-SVR并行化的光伏发电功率预测模型(MapReduce and GOA-SVR,MR-GOA-SVR),从而提高海量高维光伏发电数据的处理能力。将影响光伏输出功率的11个气象因素作为GOA-SVR的输入向量,光伏输出功率作为GOA-SVR的输出向量,建立GOA-SVR的光伏发电功率预测模型。研究结果表明:MR-GOA-SVR可以有效提高不同天气类型下的光伏发电功率的预测精度,具有很强的现实性和指导意义。与PSO-SVR、GA-SVR、GOA-SVR和SVR相比,MR-GOA-SVR在晴天、阴天和雨天均可以提高预测精度,且具有优异的并行性能。
