基于神经网络模型与最短路径模型下的公交路线设计

本文针对当前城市中人口分布不均衡、交通拥堵背景下公交线路的选优问题,本着以方便居民出行作为设计原则,拥堵节点判定模型,点-线-面整合优化模型,复杂网络模型,神经网络交通流拥堵学习模型以及最短路径计算模型设计了一套公交线路免拥堵选优模型,使得基于本模型得出的公交路线生成方案在运用中所遇到的拥堵交通量的加权平均量最小。在本模型的基础上结合ArcGIS技术,数据库技术以C#作为为宿主框架编程语言,MATLAB和C++作为为嵌入式动态链接库封装语言设计开发了一套充分考虑拥堵因素和居民小区分布的公交地理信息系统软件,以笔者所在成都市为例,进行部分公交路线的选优方案设计,并与原有路线进行了方案比较。     

机器人精密减速器单工位测试流程优化方法

为提高精密减速器性能测试效率,提出一种单工位测试流程优化方法。基于测试项目序列描述定义,构建测试流程网络,将流程转化为起点与终点固定的最短路径的旅行商问题(travelling salesman problem, TSP)模型进行优化求解,通过最优解改进找到最优测试路径。该方法能够通过测试项目的序列描述,发掘出不同项目之间优化合并空间,最优解改进克服一般TSP模型仅对相邻项目间优化的问题。应用结果表明,该方法对精密减速器动态测试项目进行优化,可以缩短16.17%测试时间。     

考虑拥堵情形的污染路径问题及其求解算法

考虑拥堵情形的污染路径问题是经典的带时间窗车辆调度问题的一个扩展。该问题的目标函数包括车辆行驶产生的排放成本,约束条件则包括交通拥堵带来的车辆行驶速度约束——该拥堵只与时间有关(time-dependent),且拥堵的开始时刻和结束时刻都可以自由设定。首先提出了拥堵情形下的行驶时间计算模型,在此基础上建立污染路径问题的线性规划模型,并提出了基于节点时间窗变换以及速度和出发时间优化的求解算法。算例结果验证了该算法的高效性。     

城市实时交通路网车辆路径优化问题研究

针对日益突出的城市交通拥堵问题,在综合考虑距离、载重量、时间、燃料对成本影响的基础上,研究时变车辆路径优化问题,提出跨时间域计算配送成本的方法,建立以成本为目标的城市配送优化模型。为提高算法的求解质量与效率,采用改进遗传算法,并设计两边逐次修正算子。最后,结合京东在重庆市的配送实例,分析车辆出发时间对成本的影响,同时考虑路径选择的灵活性并及时调整路线。实例验证了模型在城市配送中的适用性。     

基于悬架运动模型的传动轴空间动态运动分析和优化

为提高传动轴空间布置的合理性和适应性, 优化设计需要结合悬架的空间运动特性.从板簧汽车实际行驶的动态工况出发,对汽车板簧进行了运动学分析,建立基于悬架空间运动模型的传动轴运动模型,并提出了传动轴动态空间的优化目标,利用线性加权的方法,将多目标优化问题转化为单目标优化问题,选择小种群遗传算法作为优化算法.实例计算得到了平均当量夹角更小的传动布置方案,有效减小了振动和噪声.优化结果表明：基于板簧运动的传动轴空间动态设计,比传统的单一载荷下的优化设计更为合理,优化效率更高,并且优化结果的适应性更好.     

双区型仓库动态拣货策略的设计及路径优化研究

目的 针对双区型仓库,以拣货时间最短为目标函数构建数学模型,进一步提高拣货效率。方法 提出并设计动态货位调整与人工拣货协同作业的动态拣货策略,分别采用GA算法和GASA算法进行最优化求解。结果 GASA算法优于GA算法,拣货单为1张情况下的拣货时间可减少4%;与静态拣货策略相比,拣货单为10张情况下,采用GASA算法时,文中设计动态拣货策略下的拣货时间可减少6%,且随着拣货单数量的增加,拣货时间节约占比越大。结论 GASA算法较GA算法其求解动态拣货路径优化问题更高效、优化结果更好。文中所提动态拣货策略更方便实施,在静态拣货路径优化基础上,可进一步提高拣货效率,且拣货单越多,效果就越显著。     

外卖配送路径多目标实时优化研究

随着外卖行业的不断发展,外卖配送的路径优化问题已引起学者们的广泛关注。但现有研究未将骑手的目标考虑在内,且未考虑动态场景下多目标如何设定权重的问题。因此,本文对外卖配送路径的多目标实时优化进行深入研究。建立多目标外卖配送路径优化模型。该模型不仅考虑订单履行时间、平台利润和骑手服务质量3个常用的目标,另外增加骑手等待时间和骑手空驶距离这两个目标,充分将外卖平台、顾客和骑手的目标综合考虑。设计动态调整权重的多目标外卖配送路径启发式算法,解决动态场景下多目标权重如何设定的问题。通过外卖配送的实时数据进行算例分析。结果表明,本文提出的算法可以有效对多目标的外卖配送问题进行实时路径优化,且订单的密集程度对骑手等待时间和订单履行时间有直接的影响。     

基于突发事件的城市地铁客流应急疏散模型与仿真分析

面向地铁突发事件，以组合建模的视角研究地铁客流应急疏散问题。首先对突发客流及其疏散的影响因素进行分析，运用元胞自动机理论构建了地铁客流应急疏散的组合模型，包括行人最优路径选择模型、行人移动模型、障碍物绕行模型、变道和超越模型等。然后以西安市青龙寺地铁站为例进行实证分析，采用AnyLogic软件平台仿真分析了地铁客流应急疏散的过程。研究结果表明：在紧急疏散过程中，行人密度比较大的状态下，出口及路径等关键信息如果不能完全掌握，将导致站台层与站厅层间的通道出现拥挤现象。当及时发布疏散的实时信息，工作人员现场控制出站人流行走的通道和秩序时，拥堵人群可以得到有效疏散。     

出行者向诱导转移的委托代理模型研究

交通诱导的关键在于确定诱导分流的最优路径,从而尽快分流拥堵车辆,减少拥堵所带来的损失和影响．目前面临的难题为交通系统的诱导接受率问题,路径诱导接受率指提供的路径规划是否满足出行者的出行需求．利用委托代理理论,将管理者作为委托人,出行者作为代理人,建立管理者--出行者的委托代理模型,并对管理者实施政策的成本系数、激励系数、出行者的风险规避度、努力成本系数以及产出的不确定性对结果的影响进行数值实验,分析了其对路径诱导接受率的影响,研究表明管理者应尽可能以低成本有针对性的让区域内尽可能多的出行者接受路径诱导,实现政策的高效性,以提高诱导接受率．     

基于等效静态载荷法的多相材料结构动态拓扑优化设计

为了满足多相材料结构动态性能要求,提出一种基于等效静态载荷法的多相材料结构动态拓扑优化设计方法。采用序列固体各向同性料插值模型惩罚刚度矩阵和质量矩阵,以多个动载荷作用的多相材料结构总动态柔顺度最小化为优化目标,以结构质量和成本为约束条件,构建多相材料结构动态拓扑优化模型,利用等效静态载荷法将多相材料结构动态拓扑优化问题转化为多工况下的多相材料结构静态拓扑优化问题,以降低灵敏度分析的复杂程度;采用移动渐近线算法求解多相材料结构动态拓扑优化问题。数值算例结果表明所提方法是有效性的,与传统的拓扑优化方法相比,基于等效静态载荷法的多相材料结构动态拓扑优化求解时间节省了75%,大大提高了计算效率;与单相材料拓扑优化结果相比,多相材料结构动态拓扑优化设计获得的结构具有更好的动态性能。     

Traffic Management in Internet of Vehicles Using Improved Ant Colony Optimization

The Internet of Vehicles (IoV) is a networking paradigm related to the intercommunication of vehicles using a network. In a dynamic network, one of the key challenges in IoV is traffic management under increasing vehicles to avoid congestion. Therefore, optimal path selection to route traffic between the origin and destination is vital. This research proposed a realistic strategy to reduce traffic management service response time by enabling real-time content distribution in IoV systems using heterogeneous network access. Firstly, this work proposed a novel use of the Ant Colony Optimization (ACO) algorithm and formulated the path planning optimization problem as an Integer Linear Program (ILP). This integrates the future estimation metric to predict the future arrivals of the vehicles, searching the optimal routes. Considering the mobile nature of IOV, fuzzy logic is used for congestion level estimation along with the ACO to determine the optimal path. The model results indicate that the suggested scheme outperforms the existing state-of-the-art methods by identifying the shortest and most cost-effective path. Thus, this work strongly supports its use in applications having stringent Quality of Service (QoS) requirements for the vehicles.     

Turning-lane and signal optimization at intersections with multiple objectives

Traffic congestion at intersections is a serious problem in cities. In order to discharge turning vehicles efficiently at intersections to relieve traffic jams, multiple left-turn and right-turn lanes are often used. This article proposes a novel multi-objective optimization method for signal setting and multiple turning-lane assignment at intersections based on microscopic traffic simulations and a cell-mapping method. Vehicle conflicts and pedestrian interference are considered. The intersection multi-objective optimization problem (MOP) is formulated. The cell-mapping method is adopted to solve the MOP. Three measures of traffic performance are studied including transportation efficiency, energy consumption and road safety. The influence of turning-lane assignment on intersection performance is investigated in the optimization. Significant impacts of the number of turning lanes on the traffic are observed. An algorithm is proposed to assist traffic engineers to select and implement the optimal designs. In general, more turning lanes help increase turning traffic efficiency and lower fuel consumption in most cases. Remarkable improvement in traffic performance can be achieved with combined optimization of lane assignment and signal setting, which cannot be obtained with signal setting optimization alone. The studies reported in this article provide general guidance for intersection planning and operation. The proposed optimization methodology represents a promising emerging technology for traffic applications.     

圆染色在城市交叉路口交通信号相位个数设计中的应用

以城市交叉路口交通信号相位的优化为背景,分析了用圆染色解决这个问题的合理性,并给出现实中了几类交叉路口的最优相位个数。     

自组网中一种基于跨层负载感知的蚁群优化路由协议

将蚁群优化和跨层优化方法结合起来,提出了一种基于跨层负载感知和蚁群优化的路由协议(CLAOR)。协议将整个路径中各节点MAC层的总平均估计时延和节点队列缓存的占用情况结合起来,共同作为路由选择和路由调整的重要度量标准进行按需路由发现和维护,通过拥塞节点丢弃蚂蚁分组以及借助部分兼具蚂蚁功能的数据分组实现正常路由表的维护等方法,减少了控制开销,增加了算法的可扩展性,较好地解决了自组网中现有基于蚁群优化的路由协议中普遍存在的拥塞问题、捷径问题和引入的路由开销问题。仿真结果表明,CLAOR在分组成功递交率、路由开销以及端到端平均时延等方面具有优良性能,能很好地实现网络中的业务流负载均衡。     

Management of traffic congestion in adaptive traffic signals using a novel classification-based approach

Traffic congestion is a critical problem which makes roads busy. Traffic congestion challenges traffic flow in urban areas. A growing urban area creates complex traffic problems in daily life. Congestion phenomena cannot be resolved only by applying physical constructs such as building bridges and motorways and increasing road capacity. It is necessary to build technological systems for transportation management to control the traffic phenomenon. In this article, a new idea is proposed to tackle traffic congestion with the aid of machine learning approaches. A new strategy based on a tree-like configuration (i.e. a decision-making model) is suggested to handle traffic congestion at intersections using adaptive traffic signals. Different traffic networks with different sizes, varying from nine to 400 intersections, are examined. Numerical results and discussion are presented to prove the efficiency and application of the proposed strategy to alleviate traffic congestion.     

Traffic Engineering in Dynamic Hybrid Segment Routing Networks

The emergence of Segment Routing (SR) provides a novel routing paradigm that uses a routing technique called source packet routing. In SR architecture, the paths that the packets choose to route on are indicated at the ingress router. Compared with shortest-path-based routing in traditional distributed routing protocols, SR can realize a flexible routing by implementing an arbitrary flow splitting at the ingress router. Despite the advantages of SR, it may be difficult to update the existing IP network to a full SR deployed network, for economical and technical reasons. Updating partial of the traditional IP network to the SR network, thus forming a hybrid SR network, is a preferable choice. For the traffic is dynamically changing in a daily time, in this paper, we propose a Weight Adjustment algorithm WASAR to optimize routing in a dynamic hybrid SR network. WASAR algorithm can be divided into three steps: firstly, representative Traffic Matrices (TMs) and the expected TM are obtained from the historical TMs through ultra-scalable spectral clustering algorithm. Secondly, given the network topology, the initial network weight setting and the expected TM, we can realize the link weight optimization and SR node deployment optimization through a Deep Reinforcement Learning (DRL) algorithm. Thirdly, we optimize the flow splitting ratios of SR nodes in a centralized online manner under dynamic traffic demands, in order to improve the network performance. In the evaluation, we exploit historical TMs to test the performance of the obtained routing configuration in WASAR. The extensive experimental results validate that our proposed WASAR algorithm has superior performance in reducing Maximum Link Utilization (MLU) under the dynamic traffic.     

Q-Learning Based Routing Protocol for Congestion Avoidance

The end-to-end delay in a wired network is strongly dependent on congestion on intermediate nodes. Among lots of feasible approaches to avoid congestion efficiently, congestion-aware routing protocols tend to search for an uncongested path toward the destination through rule-based approaches in reactive/incident-driven and distributed methods. However, these previous approaches have a problem accommodating the changing network environments in autonomous and self-adaptive operations dynamically. To overcome this drawback, we present a new congestion-aware routing protocol based on a Q-learning algorithm in software-defined networks where logically centralized network operation enables intelligent control and management of network resources. In a proposed routing protocol, either one of uncongested neighboring nodes are randomly selected as next hop to distribute traffic load to multiple paths or Q-learning algorithm is applied to decide the next hop by modeling the state, Q-value, and reward function to set the desired path toward the destination. A new reward function that consists of a buffer occupancy, link reliability and hop count is considered. Moreover, look ahead algorithm is employed to update the Q-value with values within two hops simultaneously. This approach leads to a decision of the optimal next hop by taking congestion status in two hops into account, accordingly. Finally, the simulation results presented approximately 20% higher packet delivery ratio and 15% shorter end-to-end delay, compared to those with the existing scheme by avoiding congestion adaptively.     

A Dendrite Net based decoupled framework for the reliability-based control co-design problem

To improve the reliability of the dynamic system including physical and control design, the reliability-based control co-design (RB-CCD) problem has been studied to account for the uncertainty stemming from the random physical design. However, when encountering RB-CCD in the sophisticated system in which the dynamic model simulation is time-consuming or the state equation is expressed implicitly, the available RB-CCD methods will consume significant computational effort to perform numerous system simulations for the reliability analysis and deterministic optimization. Therefore, this work proposes a Dendrite Net-based decoupled framework for RB-CCD to alleviate the computational burden. Specifically, the Dendrite (DD) model constructed by the suggested training scheme integrated with an adaptive sampling strategy is used to approximate the state equation in the dynamic system. After that, the sequential optimization and reliability assessment method decouples RB-CCD into the control co-design (CCD) problem and time-dependent reliability assessment problem, which are solved sequentially based on the cheap estimations of DD model, rather than the expensive simulations of the original system. Furthermore, two numerical examples and an engineering example of 3-DOF robot system are applied to demonstrate the feasibility and efficiency of the proposed framework.     

Energy-efficient frozen food transports: the Refrigerated Routing Problem

Given the growing importance of cold chains and the need to promote sustainable processes, energy efficiency in refrigerated transports is investigated at operational level. The Refrigerated Routing Problem is defined, involving multi-drop deliveries of palletised unit loads of frozen food from a central depot to clients. The objective is to select the route with minimum fuel consumption for both traction and refrigeration. The problem formulation considers speed variation due to traffic congestion phenomena, as well as decreasing load on board along the route as successive clients are visited. Transmission load for exposure of the vehicle to outdoor temperatures and infiltration load at door opening are modelled, taking into account outdoor conditions varying along the day and the year. The resulting multi-period problem is modelled and solved by means of Constraint Programming. Test scenarios come from a real local network for frozen bread dough distributed to supermarkets. Results show how fuel minimisation leads to the selection of different routes in comparison to the traditional total travel distance or time objectives. Energy savings are affected by demand distribution among the clients, departure time, number of visits per tour, seasonality and location of the delivery network.     

A Neuro-Fuzzy Approach to Road Traffic Congestion Prediction

The fast-paced growth of artificial intelligence applications provides unparalleled opportunities to improve the efficiency of various systems. Such as the transportation sector faces many obstacles following the implementation and integration of different vehicular and environmental aspects worldwide. Traffic congestion is among the major issues in this regard which demands serious attention due to the rapid growth in the number of vehicles on the road. To address this overwhelming problem, in this article, a cloud-based intelligent road traffic congestion prediction model is proposed that is empowered with a hybrid Neuro-Fuzzy approach. The aim of the study is to reduce the delay in the queues, the vehicles experience at different road junctions across the city. The proposed model also intended to help the automated traffic control systems by minimizing the congestion particularly in a smart city environment where observational data is obtained from various implanted Internet of Things (IoT) sensors across the road. After due preprocessing over the cloud server, the proposed approach makes use of this data by incorporating the neuro-fuzzy engine. Consequently, it possesses a high level of accuracy by means of intelligent decision making with minimum error rate. Simulation results reveal the accuracy of the proposed model as 98.72% during the validation phase in contrast to the highest accuracies achieved by state-of-the-art techniques in the literature such as 90.6%, 95.84%, 97.56% and 98.03%, respectively. As far as the training phase analysis is concerned, the proposed scheme exhibits 99.214% accuracy. The proposed prediction model is a potential contribution towards smart cities environment.