With the evolution of the network,network traffic is exploding,and routing method has become a key problem in network traffic control. This is because the traditional routing strategy does not have the ability to learn,and cannot learn network anomalies such as congestion and link interruption from the forwarding experience in the past,so the routing strategy cannot be adjusted accord-ing to the network state. In this paper,we present a routing algorithm,Double Adaptive Learning Rate Q-routing(DALRQ-routing). During the Echo phase,DALRQ-routing adjusts the echo learning rate according to the network delay to reduce the delay jitter caused by the echo operation. In the transfer phase,the transfer learning rate is adjusted according to TD-error to improve the convergence speed of the algorithm. The delay jitter is reduced and the convergence of the algorithm is accelerated by the cooperation of two learn-ing rate adaptive mechanism. The algorithm proposed in this paper is compared with Full Echo Q-routing and AQFE algorithm. The experiment result shows that the algorithm proposed in this paper can reduce delay jitter and improve the stability of the network on the basis of maintaining high convergence speed and low initialization peak delay under dynamic network load.

To reduce the increasingly congestion in cities, it is essential for intelligent transportation system (ITS) to accurately forecast the short-term traffic flow to identify the potential congestion sites. In recent years, the emerging deep learning method has been introduced to design traffic flow predictors, such as recurrent neural network (RNN) and long short-term memory (LSTM), which has demonstrated its promising results. In this paper, different from existing work, we study the temporal convolutional network (TCN) and propose a deep learning framework based on TCN model for short-term city-wide traffic forecast to accurately capture the temporal and spatial evolution of traffic flow. Moreover, we design the model with the Taguchi method to develop an optimized structure of the TCN model, which not only reduces the number of experiments, but also yields high accuracy of forecasting results. With the real-world traffic flow data collected from highways in Birmingham City of U.K., we compare our model with four deep learning based models including LSTM models, GRU models, SAE models, DeepTrend and CNN-LSTM models in terms of the mean absolute error (MAE) and mean relative error (MRE) regarding the actual flow data. The experimental results demonstrate that our framework achieves the state-of-art performance with superior accuracy in short-term traffic flow forecasting.

The rapid growth of the number of vehicles in cities will bring about a series of traffic problems,including traffic conges-tion,traffic accidents,etc. Efficient traffic signal control method has been proved to be one of the important ways to alleviate traffic problems. The existing signal control mainly focuses on the design of online signal control algorithm,but there is a problem of frequent switching of traffic lights. This article first predicts the number of vehicles in the detection area for the next time period based on the cooperative driving and lane changing model,and then uses the graph theory to model the traffic movement at the intersection. On the basis of this model,a highly efficient vehicle scheduling algorithm based on graph is designed. The approximation ratio of the algo-rithm is proved to be 2. The experimental results show that:first,the vehicle scheduling algorithm proposed in this paper can effectively reduce the time of scheduling the vehicles and improve the efficiency of traffic. Secondly,the algorithm can greatly reduce the number of switching of traffic lights.

研究表明,历史流量数据可以用于移动网络流量的预测,同时周边区域的流量信息可以提高流量预测的准确性.为此,文中提出一种基于时空特征的移动网络流量预测模型STFM.STFM模型利用目标区域及周围区域的历史移动网络流量对目标区域的流量进行预测.其核心思想是,首先利用三维卷积网络(3D CNN)从流量中提取移动网络流量空间上的特征,再利用时间卷积网络(TCN)提取移动网络流量时间上的特征,最后全连接层对提取的特征与实际的流量值建立映射关系,产生预测的流量值.根据实验的验证与分析,STFM在移动网络流量预测上的标准均方根误差(NRMSE)相比TCN,CNN和CNN-LSTM分别减少了28％,21.7％和10％.因此,STFM模型能够有效提高移动网络流量预测的准确率.

针对板料渐进成形中的损伤问题,从细观角度引入考虑板材各向异性的损伤模型Hill'48-GTN.对DC06板料进行单向拉伸实验和有限元模拟,通过对比两应力应变曲线来确定模型参数.然后把确定参数的GTN模型嵌入到有限元软件Abaqus中,以模拟圆台件的渐进成形过程,并对比了模拟和实验结果中的厚度分布.结果表明:所得模型参数对板材渐进成形是有效的.