基于时空耦合特性的充电站运行状态预测

提出一种基于时空耦合特性和深度学习模型的充电站运行状态预测方法。首先,基于充电站历史运行数据和所在区域的交通通行速度数据集,利用k-means聚类方法将充电站划分为不同类型,分析充电站运行状态在时间上的特性;建立单个充电站的"偏移量-交通-时间"三维矩阵模型,深度挖掘充电站运行状态与周边交通状况在时间和空间上的耦合相关性。其次,将充电站状态与交通状况的时间滞后相关特性进行空间重构,利用卷积神经网络进行特征提取,通过长短期记忆网络进行时间序列预测,构建基于Keras深度学习框架的充电站运行状态多步预测模型。最后,以20个充电站的真实运行数据进行验证,并与多种预测算法进行对比,结果表明,所提方法具有较高的预测精度。     

基于机会约束规划的含电动汽车主动配电网能量管理方法

针对含电动汽车(EV)和分布式光伏的主动配电网(ADN),提出了一种基于机会约束规划的能量管理方法。首先,基于EV用户的出行特性和需求,构建了基于分段线性化的EV智能充放电决策模型;其次,通过支路潮流模型与二阶锥松弛,构建了含EV与分布式光伏的ADN一体化数学模型,EV集群作为灵活可控单元主动参与ADN的能量管理;然后,为了充分考虑分布式光伏的不确定性,采用机会约束规划方法描述了含不确定性参数的数学模型,并对模型中的机会约束条件进行确定性转换;最后,考虑不同城市功能区内含EV与分布式光伏的ADN场景,进一步对比分析了不同的机会约束条件置信水平下EV对ADN经济安全运行的影响。仿真结果表明,适度降低机会约束条件的置信水平能在保证EV用户出行需求的同时充分地挖掘EV充放电行为的灵活性,进一步实现ADN的灵活运行。     

偏振三维成像仪的相对偏振方向定标方法

在介绍偏振三维成像机理、四孔径偏振三维成像仪组成的基础上,开展四孔径相对偏振方向对偏振三维成像精度影响分析,确定四孔径相对偏振方向精度要求。制定了四孔径镜头偏振片相对偏振方向定标方法和四孔径偏振三维成像仪相对偏振方向定标方法,搭建了定标装置,在实验室内开展了相对偏振方向定标。四孔径镜头偏振片相对偏振方向定标误差为±0.5o,四孔径偏振三维成像仪相对偏振方向误差为±1o,从而可保证偏振三维反演的法向量误差为-5.47%~5.80%,为偏振三维成像仪高质量成像提供保障。     

Energy Efficient Cluster Based Routing Protocol for WSN Using Firefly Algorithm and Ant Colony Optimization

Maximizing network lifetime is the main goal of designing a wireless sensor network. Clustering and routing can effectively balance network energy consumption and prolong network lifetime. This paper presents a novel cluster-based routing protocol called EECRAIFA. In order to select the optimal cluster heads, Self-Organizing Map neural network is used to perform preliminary clustering on the network nodes, and then the relative reasonable level of the cluster, the cluster head energy, the average distance within the cluster and other factors are introduced into the firefly algorithm (FA) to optimize the network clustering. In addition, the concept of decision domain is introduced into the FA to further disperse cluster heads and form reasonable clusters. In the inter-cluster routing stage, the inter-cluster routing is established by an improved ant colony optimization (ACO). Considering factors such as the angle, distance and energy of the node, the heuristic function is improved to make the selection of the next hop more targeted. In addition, the coefficient of variation in statistics is introduced into the process of updating pheromones, and the path is optimized by combining energy and distance. In order to further improve the network throughput, a polling control mechanism based on busy/idle nodes is introduced during the intra-cluster communication phase. The simulation experiment results prove that under different application scenarios, EECRAIFA can effectively balance the network energy consumption, extend the network lifetime, and improve network throughput.

     

Facial Expression Recognition Based on Spatial and Channel Attention Mechanisms

Wireless Personal Communications - Microarray-based gene expression profiling is an emerging method to predict, classify, diagnose and to treat cancer efficiently. The characteristics of this...     

Blockchain Security Technology Based on the Asynchronous Transmission Mode of IoT Technology in Smart Cities

Wireless Personal Communications - With the rapid development of information technology, issues such as network security and privacy protection have attracted more and more attention. The...     

无线传感网络中基于非抗窜扰智能卡的双因素认证协议

智能卡是最为常见的密码设备之一,因其抗窜扰特性,智能卡常常被用于电子商务、医疗健康以及物联网等高安全需求的领域中为安全提供服务。随着侧信道攻击、逆向工程等技术的发展,研究表明智能卡内保存的参数可恢复,使其不再具有抗窜扰特性,因而,基于非抗窜扰智能卡假设的多因素认证协议设计得到了广泛的关注。为此,研究了在无线传感网络中典型的多因素协议,指出其不能抵抗离线口令猜测攻击和中间人攻击、无法实现双向认证,以及不能抵抗离线口令猜测攻击、无法实现用户匿名性等问题。为克服这些缺陷,在非抗窜扰智能卡假设下,结合哈希链技术提出了一类面向无线传感器网络的双因素认证协议,并在随机预言机模型中给出了严格的安全证明。与现有无线传感网络环境下多因素认证协议相比,该协议在保持较低计算开销的同时,实现了更高的安全性,适于资源受限的无线传感器网络环境。