The Internet of Vehicles aims to fundamentally improve transportation by connecting vehicles, drivers, passengers, and service providers together. Several new services such as parking space identification, platooning and intersection control—to name just a few—are expected to improve traffic congestion, reduce pollution, and improve the efficiency, safety and logistics of transportation. Proposed end-user services, however, make extensive use of private information with little consideration for the impact on users and third parties (those individuals whose information is indirectly involved). This article provides the first comprehensive overview of privacy and trust issues in the Internet of Vehicles at the service level. Various concerns over privacy are formalised into four basic categories: personal information privacy, multi-party privacy, trust, and consent to share information. To help analyse services and to facilitate future research, the main relevant end-user services are taxonomised according to voluntary and involuntary information they require and produce. Finally, this work identifies several open research problems and highlights general approaches to address them. These especially relate to measuring the trade-off between privacy and service functionality, automated consent negotiation, trust towards the IoV and its individual services, and identifying and resolving multi-party privacy conflicts.
20 September 2021 in IEEE Transactions on Intelligent Transportation Systems
En-route charging stations are essential to ensure the adoption of electric vehicles. However, careful planning is necessary due to high cost in infrastructure and potentially long waiting queues. Existing literature on the placement of charging stations largely disregards competition, sets prices to cover costs and/or disregards queues. In contrast, this work models competing station investors who aim to maximise expected profit, while electric vehicle drivers aim to minimise expected travel costs including queues. Following a game-theoretic approach, investors strategically decide station capacities, locations and charging unit power outputs as well as fees, taking into consideration building and operational costs. Given the complexity of the problem, the solution involves a combination of theoretical and algorithmic techniques to obtain subgame-perfect equilibria of investor and driver choices. Subgame-perfect equilibria are found to be at least 92.85% efficient, for reasonable fluctuations of problem parameters. Furthermore, it is found that charging prices can be up to approximately 5 times higher than marginal cost due to long charging times, and also that better charging technology may not necessarily benefit drivers in the near future. Finally, subsidies towards the purchase of charging units are shown to be beneficial for both drivers and investors, being able to generate up to 14.3% additional value than the cost of the subsidy. In contrast, subsidies on the energy price for stations are found to have small effect and can be abused by investors.
Marine voyage optimization determines the optimal route and speed to ensure timely arrival. The problem becomes particularly complex when incorporating a dynamic environment, such as future expected weather conditions along the route and unexpected disruptions. This study explores two model-free Deep Reinforcement Learning (DRL) algorithms: (i) a Double Deep Q Network (DDQN) and (ii) a Deep Deterministic Policy Gradient (DDPG). These algorithms are computationally costly, so we split optimization into an offline phase (costly pre-training for a route) and an online phase where the algorithms are fine-tuned as updated weather data become available. Fine tuning is quick enough for en-route adjustments and for updating the offline planning for different dates where the weather might be very different. The models are compared to classical and heuristic methods: the DDPG achieved a 4% lower fuel consumption than the DDQN and was only outperformed by Tabu Search by 1%. Both DRL models demonstrate high adaptability to dynamic weather updates, achieving up to 12% improvement in fuel consumption compared to the distance-based baseline model. Additionally, they are non-graph-based and self-learning, making them more straightforward to extend and integrate into future digital twin-driven autonomous solutions, compared to traditional approaches.
Digital twins can help ports, operators and their customers streamline processes, improve safety, and reduce emissions in transport operations that involve at least a maritime leg. This chapter discusses the necessary context for regulations, port operations, and hinterland capabilities; and frames a general methodology under this context for how port authorities, terminal operators, shipping companies, and logistics operators can implement collaborative, emission reducing practices such as slow steaming and synchro-modality. In short, a federation of digital twins that allows to move information downstream from the ship to the port, then to the hinterland infrastructure as well as upstream the opposite way can enable new levels of operational readiness and efficiency, and importantly environmental compliance. At the same time, apart from the improved general efficiency of all processes associated with transport, shipowners can minimise the need to retrofit existing ships for them to remain compliant with the emissions regulations which are bound to be stricter each passing year.