Analytics and machine learning in vehicle routing research

Bai, Ruibin; Chen, Xinan; Chen, Zhilong; Cui, Tianxiang; Gong, Shuhui; Wang, He; Jiang, Xiaoping; Jin, Huan; Jin, Jiahuan; Kendall, Graham; Li, Jiawei; Lu, Zheng Feng; Ren, Jianfeng; Weng, Paul; Xue, Ning; Zhang, Huayan

doi:10.1080/00207543.2021.2013566

Cited by 65 publications

(19 citation statements)

References 166 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They then formulated an optimization problem that minimizes the weighted sum of the service time and energy consumption in the caching-assisted VEC system and used a genetic algorithm to solve the problem. The authors of [ 34 ] presented a comprehensive review and analysis of the vehicle routing problem (VRP). They mainly reviewed machine learning-assisted VRP modeling and optimization approaches.…”

Section: Related Workmentioning

confidence: 99%

Energy-Efficient Resource Allocation Based on Deep Q-Network in V2V Communications

Han

2023

Sensors

View full text Add to dashboard Cite

Recently, with the development of autonomous driving technology, vehicle-to-everything (V2X) communication technology that provides a wireless connection between vehicles, pedestrians, and roadside base stations has gained significant attention. Vehicle-to-vehicle (V2V) communication should provide low-latency and highly reliable services through direct communication between vehicles, improving safety. In particular, as the number of vehicles increases, efficient radio resource management becomes more important. In this paper, we propose a deep reinforcement learning (DRL)-based decentralized resource allocation scheme in the V2X communication network in which the radio resources are shared between the V2V and vehicle-to-infrastructure (V2I) networks. Here, a deep Q-network (DQN) is utilized to find the resource blocks and transmit power of vehicles in the V2V network to maximize the sum rate of the V2I and V2V links while reducing the power consumption and latency of V2V links. The DQN also uses the channel state information, the signal-to-interference-plus-noise ratio (SINR) of V2I and V2V links, and the latency constraints of vehicles to find the optimal resource allocation scheme. The proposed DQN-based resource allocation scheme ensures energy-efficient transmissions that satisfy the latency constraints for V2V links while reducing the interference of the V2V network to the V2I network. We evaluate the performance of the proposed scheme in terms of the sum rate of the V2X network, the average power consumption of V2V links, and the average outage probability of V2V links using a case study in Manhattan with nine blocks of 3GPP TR 36.885. The simulation results show that the proposed scheme greatly reduces the transmit power of V2V links when compared to the conventional reinforcement learning-based resource allocation scheme without sacrificing the sum rate of the V2X network or the outage probability of V2V links.

show abstract

Section: Related Workmentioning

confidence: 99%

Energy-Efficient Resource Allocation Based on Deep Q-Network in V2V Communications

Han

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Bai et al [121] [109] 2020 Congestion detection using public cameras CNN Gatto and Forster [110] 2021 Congestion detection using audio features RF Leung et al [111] 2020 Trolley bus delay prediction Fuzzy-logic Wu et al [112] 2019 Urban railway delay prediction C-LSTM+Encoder-Decoder Zhao et al [116] 2019 Real-time traffic forecasting t-GCN Zhao et al [119] 2019 Routing management Q-Learning Hussein et al [122] 2022 Ambulance vehicle routing DNN Hussein et al [123] 2022 Ambulance vehicle routing BA-CNN Nallaperume et al [125] 2019 Smart traffic control Q-learning Hussein [122] investigates how machine learning can help find the shortest travelling time for ambulance vehicles (AV). In their first ML based approach, they developed a neural network based model that can suggest optimal travelling path based on information about the accident, the injured patients and on position describers.…”

Section: Infrastructure Levelmentioning

confidence: 99%

Machine Learning Use-Cases in C-ITS Applications

Bereczki¹,

Simon²

2023

Infocommunications journal

View full text Add to dashboard Cite

In recent years, the development of Cooperative Intelligent Transportation Systems (C-ITS) have witnessed significant growth thus improving the smart transportation concept. The ground of the new C-ITS applications are machine learning algorithms. The goal of this paper is to give a structured and comprehensive overview of machine learning use-cases in the field of C-ITS. It reviews recent novel studies and solutions on CITS applications that are based on machine learning algorithms. These works are organised based on their operational area, including self-inspection level, inter-vehicle level and infrastructure level. The primary objective of this paper is to demonstrate the potential of artificial intelligence in enhancing C-ITS applications.

show abstract

“…Research on using machine and (deep) RL approaches for tackling hard combinatorial optimization problems (e.g., traveling salesman problem, knapsack) is emerging (e.g., combining neural combinatorial optimization with RL [23]). Bai et al [24] review hybrid methods that are combining analytical techniques with machine learning tools in addressing Vehicle Routing Problems (VRP) and discuss the emerging research in regard to machine learning assisted VRP modelling and optimization. Bengio et al [25] surveyed attempts to combine approaches to leverage machine learning to solve combinatorial optimization problems and propose a methodology to integrate approaches.…”

Section: A Reinforcement Learningmentioning

confidence: 99%

A Reinforcement Learning Platform for Small and Medium-sized Enterprises in Logistics

Piest

Iacob

Sinderen

et al. 2021

2021 IEEE 25th International Enterprise Distributed Object Computing Workshop (EDOCW)

View full text Add to dashboard Cite

While real-time data and sophisticated Reinforcement Learning (RL) approaches are emerging, logistic organizations, in particular Small and Medium-size d Enterprises (SMEs), lack the tools and expertise to effectively identify whether (parts of) their business processes are suitable for using RL and adopt these approaches in their daily practice. This paper presents the results of our efforts to design, develop, test and implement a RL-based decision support platform based on the Open Trip Model (OTM) for the logistics industry . The main contribution of this paper is a potentially generalizable platform architecture and instantiation of the following main functional components: 1) a graphical user interface to access platform services, 2) APIs to automate the data collection based on the OTM, 3) an OTM compliant data storage, 4) a repository and tool for testing multiple algorithms and perform (hyper)parameter tuning, and 5) infrastructure provisioning to run and monitor agents. The platform is complemented with RL guidelines to transfer the platform, knowledge, and practices to SMEs. The platform architecture is validated with a panel of experts and demonstrated in use in a case study at a logistics services provider. The platform demonstration and case study contribute to increasing awareness of potential applications of RL in the logistics industry. The platform provides a foundation for empirical research and experimental development of RL approaches in logistics. Future research will focus on alternative and hybrid approaches, federated learning, and incorporating data sharing concepts as part of the envisioned federated data sharing infrastructure for the Dutch logistics industry.

show abstract

Analytics and machine learning in vehicle routing research

Cited by 65 publications

References 166 publications

Energy-Efficient Resource Allocation Based on Deep Q-Network in V2V Communications

Energy-Efficient Resource Allocation Based on Deep Q-Network in V2V Communications

Machine Learning Use-Cases in C-ITS Applications

A Reinforcement Learning Platform for Small and Medium-sized Enterprises in Logistics

Contact Info

Product

Resources

About