Search results

The purpose of this paper is to present the development of an architecture for real‐time routing of automated guided vehicles (AGV) in a random flexible manufacturing system (FMS).

AGV routing problem is modeled using an evolutionary algorithm‐based intelligent path planning model, which handles vehicle assignments to material handling requests and makes routing decisions with the objective of maximizing the system throughput. The architecture is implemented on a 3‐layer software environment in order to evaluate the effectiveness of the proposed model.

The proposed architecture, along with the evolutionary algorithm‐based routing model, is implemented in a simulated FMS environment using hypothetical production data. In order to benchmark the performance of the path planning algorithm, the same FMS model is run by traditional dispatching rules. The analysis shows that the proposed routing model outperforms the traditional dispatching rules for real‐time routing of AGVs in many cases.

Future work includes expanding the scope of the current work by developing and implementing other routing models and benchmarking them against the proposed model on different performance measures.

The implementation of evolutionary algorithms in real‐time routing of AGVs is unique. In addition, due to its modularity, the proposed 3‐layer architecture can allow effective and efficient integration of different real‐time routing algorithms; therefore it can be used as a benchmarking platform.

A cross-domain intelligent software-defined network (SDN) routing method based on a proposed multiagent deep reinforcement learning (MDRL) method is developed.

First, the network is divided into multiple subdomains managed by multiple local controllers, and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement mechanism. Then, a cooperative communication module is designed to realize message transmission and message synchronization between the root and local controllers, and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to acquire global network state information in real time. Finally, after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers, a network traffic state prediction mechanism is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real time.

Experimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and open shortest path first (OSPF) routing methods.

Message transmission and message synchronization for multicontroller interdomain routing in SDN have long adaptation times and slow convergence speeds, coupled with the shortcomings of traditional interdomain routing methods, such as cumbersome configuration and inflexible acquisition of network state information. These drawbacks make it difficult to obtain global state information about the network, and the optimal routing decision cannot be made in real time, affecting network performance. This paper proposes a cross-domain intelligent SDN routing method based on a proposed MDRL method. First, the network is divided into multiple subdomains managed by multiple local controllers, and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement mechanism. Then, a cooperative communication module is designed to realize message transmission and message synchronization between root and local controllers, and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to realize the real-time acquisition of global network state information. Finally, after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers, a prediction mechanism for the network traffic state is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real time. Experimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and OSPF routing methods.

Using a real-time road network combined with historical traffic data for Al-Salt city, the paper aims to propose a new federated genetic algorithm (GA)-based optimization technique to solve the dynamic vehicle routing problem. Using a GA solver, the estimated routing time for 300 chromosomes (routes) was the shortest and most efficient over 30 generations.

In transportation systems, the objective of route planning techniques has been revised from focusing on road directors to road users. As a result, the new transportation systems use advanced technologies to support drivers and provide them with the road information they need and the services they require to reduce traffic congestion and improve routing problems. In recent decades, numerous studies have been conducted on how to find an efficient and suitable route for vehicles, known as the vehicle routing problem (VRP). To identify the best route, VRP uses real-time information-acquired geographical information systems (GIS) tools.

This study aims to develop a route planning tool using ArcGIS network analyst to enhance both cost and service quality measures, taking into account several factors to determine the best route based on the users’ preferences.

Furthermore, developing a route planning tool using ArcGIS network analyst to enhance both cost and service quality measures, taking into account several factors to determine the best route based on the users’ preferences. An adaptive genetic algorithm (GA) is used to determine the optimal time route, taking into account factors that affect vehicle arrival times and cause delays. In addition, ArcGIS' Network Analyst tool is used to determine the best route based on the user's preferences using a real-time map.

The paper examines the circumstances of success in telematic use and strategic effects resulting from the implementation and use of such technologies from SMEs in the Greek Market.

The analysis is based on a three‐phased triangulated research methodology; that is literature review, interviews from 15 logistics directors and a questionnaire survey of 73 logistics SMEs in Greece.

The basic finding that has been derived from both phases 2 and 3 (survey and interviews) is that although the penetration of telematics is still low in Greece, logistics operators understand the importance of mobile services and they already know which they plan to their customers.

An inherent limitation of this survey is the fact that it address, like all surveys, the requirements of its respondents only, without taking into account.

This paper explores customer perceptions and requirements for the implementation of mobile real‐time support services for city logistics. The requirements, elicited by the results of the survey, are used to propose a systemic representation of a real‐time vehicle management mechanism for urban transportation.

This paper studies low-carbon vehicle routing problem (VRP) for cold chain logistics with the consideration of the complexity of the road network and the time-varying traffic conditions, and then a low-carbon cold chain logistics routing optimization model was proposed. The purpose of this paper is to minimize the carbon emission and distribution cost, which includes vehicle operation cost, product freshness cost, quality loss cost, penalty cost and transportation cost.

This study proposed a mathematical optimization model, considering the distribution cost and carbon emission. The improved Nondominated Sorting Genetic Algorithm II algorithm was used to solve the model to obtain the Pareto frontal solution set.

The result of this study showed that this model can more accurately assess distribution costs and carbon emissions than those do not take real-time traffic conditions in the actual road network into account and provided guidance for cold chain logistics companies to choose a distribution strategy and for the government to develop a carbon tax.

There are some limitations in the proposed model. This study assumes that there are only one distribution and a single type of vehicle.

Existing research on low-carbon VRP for cold chain logistics ignores the complexity of the road network and the time-varying traffic conditions, resulting in nonmeaningful planned distribution routes and furthermore low carbon cannot be discussed. This study takes the complexity of the road network and the time-varying traffic conditions into account, describing the distribution costs and carbon emissions accurately and providing the necessary prerequisites for achieving low carbon.

The purpose of this paper is to take advantage of Internet of Things (IoT) for intelligent route programming of crowd emergency evacuation in metro station. It is a novel approach to ensure the crowd safety and reduce the casualties in the emergency context. An evacuation route programming model is constructed to select a suitable evacuation route and support the emergency decision maker of metro station.

The IoT technology is employed to collect and screen information, and to construct an expert decision model to support the metro station manager to make decision. As a feasible way to solve the multiple criteria decision-making problem, an improved multi-attributive border approximation area comparison (MABAC) approach is introduced.

The case study indicates that the model provides valuable suggestions for evacuation route programming and offers practical support for the design of an evacuation route guidance system. Moreover, IoT plays an important role in the process of intelligent route programming of crowd emergency evacuation in metro station. A library has similar structure and crowd characteristics of a metro station, thus the intelligent route programming approach can be applied to the library crowd evacuation.

The highlights of this paper are listed as followings: the accuracy and accessibility of the metro station’s real-time information are improved by integrating IoT technology with the intelligent route programming of crowd emergency evacuation. An improved MABAC approach is introduced to the expert support model. It promotes the applicability and reliability of decision making for emergency evacuation route selection in metro station. It is a novel way to combine the decision-making methods with practice.

Vehicle routing (VR) is critical in successful logistics execution. The emergence of technologies and information systems allowing for seamless mobile and wireless connectivity between delivery vehicles and distribution facilities is paving the way for innovative approaches to real‐time VR and distribution management. This paper investigates avenues for building upon recent trends in VR‐related research towards an integrated approach to real‐time distribution management. A review of the advances to‐date in both fields, i.e. the relevant research in the VR problem and the advances in mobile technologies, forms the basis of this investigation. Further to setting requirements, we propose a system architecture for urban distribution and real‐time event‐driven vehicle management.

The purpose of this study is to provide real-time route guidance within city to help commuters.

In urban areas to avoid road congestion and to reach the destination on time, intelligent transport system (ITS) utilizes recent advanced technology. To support this, existing route guidance system (RGS) suggests alternative route to commuters. However, ITS requires a system which suggests the alternative route along with the mode of transport such as public, private, taxi services etc. Integrated mode of transport (IMT) implemented in this paper guides the commuters of urban area with the best mode of transport. Inputs to our IMT predictive model are the commuter's choice of (1) minimum travel time (2) minimum cost (3) flexible route and (4) less traffic intensity along with source and destination locations. Based on these user inputs, IMT predictive model suggests optimal mode of transport. In this paper to implement the IMT model, we have considered the transport facility available in Bangalore, a city in India. The city has metro train, bus and taxi services available to the commuters. Implementation is divided into two parts. In the first part, the model checks for the end-to-end connectivity/availability of metro train facility. If metro train connectivity exists, the model concludes this as the best mode of travel. In the second part, for the routes which are not connected by metro train, the optimal mode of transport through road network will be suggested. In the first part, to check the existence of metro train along the routes between source and destination, location-IQ API is used. In the later part, to suggest transport along the road network, Q-learning algorithm of reinforcement learning technique is used.

The findings are the predictive model algorithm to find the best mode of transfer and reinforcement model used in real time route guidance system.

This is a new Idea, not proposed in any research work.

The purpose of this paper is to present the design and evaluation of an integrated system that supports planners and dispatchers to deliver enhanced courier operations. In addition to regular deliveries and pickups, these operations include: first, mass deliveries to be served over a horizon of multiple days; and second, real-time dynamic requests (DRs) to be served within the same service period.

To address the aforementioned challenges, the authors developed an architecture that enhances a typical fleet management system by integrating purpose designed methods. Specifically, the authors plan mass deliveries taking into account typical routes of everyday operations. For planning DRs in real time, the authors propose an efficient insertion heuristic.

The results from testing the proposed optimization algorithms for planning mass deliveries and real-time DRs are encouraging, since the proposed algorithms outperform current practices. Testing in a practical courier environment, indicated that the enhanced planning system may improve significantly operational performance.

The proposed optimization algorithm for the dynamic aspect of this problem comprises a heuristic approach that reaches suboptimal solutions of high quality. The development of fast optimal algorithms for solving these very interesting and practical problems is a promising area for further research.

The proposed integrated system addresses significant problems of hybrid courier operations in an integrated, balanced manner. The tests showed that the allocation of flexible orders within a three-day time horizon improved the cost per flexible order by 7.4 percent, while computerized routing improved the cost of initial (static) routing by 14 percent. Furthermore, the proposed method for managing DRs reduced the excess cost per served request by over 40 percent. Overall, the proposed integrated system improved the total routing costs by 16.5 percent on average compared to current practices.

Both the planning problems and the related solution heuristics address original aspects of practical courier operations. Furthermore, the system integration and the proposed systematic planning contribute to the originality of the work.