Emob-Lab

In recent years, the advancement of artificial intelligence techniques has led to significant interest in reinforcement learning (RL) within the traffic and transportation community. Dynamic traffic control has emerged as a prominent application field for RL in traffic systems. This paper presents a comprehensive survey of RL studies in dynamic traffic control, addressing the challenges associated with implementing RL-based traffic control strategies in practice, and identifying promising directions for future research. The first part of this paper provides a comprehensive overview of existing studies on RL-based traffic control strategies, encompassing their model designs, training algorithms, and evaluation methods. It is found that only a few studies have isolated the training and testing environments while evaluating their RL controllers. Subsequently, we examine the challenges involved in implementing existing RL-based traffic control strategies. We investigate the learning costs associated with online RL methods and the transferability of offline RL methods through simulation experiments. The simulation results reveal that online training methods with random exploration suffer from high exploration and learning costs. Additionally, the performance of offline RL methods is highly reliant on the accuracy of the training simulator. These limitations hinder the practical implementation of existing RL-based traffic control strategies. The final part of this paper summarizes and discusses a few existing efforts which attempt to overcome these challenges. This review highlights a rising volume of studies dedicated to mitigating the limitations of RL strategies, with the specific aim of enhancing their practical implementation in recent years.

In our increasingly electrified society, lithium–ion batteries are a key element. To design, monitor or optimise these systems, data play a central role and are gaining increasing interest. This article is a review of data in the battery field. The authors are experimentalists who aim to provide a comprehensive overview of battery data. From data generation to the most advanced analysis techniques, this article addresses the concepts, tools and challenges related to battery informatics with a holistic approach. The different types of data production techniques are described and the most commonly used analysis methods are presented. The cost of data production and the heterogeneity of data production and analysis methods are presented as major challenges for the development of data-driven methods in this field. By providing an understandable description of battery data and their limitations, the authors aim to bridge the gap between battery experimentalists, modellers and data scientists. As a perspective, open science practices are presented as a key approach to reduce the impact of data heterogeneity and to facilitate the collaboration between battery scientists from different institutions and different branches of science.

We propose a novel system leveraging deep learning-based methods to predict urban traffic accidents and estimate their severity. The major challenge is the data imbalance problem in traffic accident prediction. The problem is caused by numerous zero values in the dataset due to the rarity of traffic accidents. To address the issue, we propose a grid-clustered feature map with the ideas of grids and cells. To predict the occurrence of accidents in the grid, we introduce an accident detector that combines the power of a Convolutional Neural Network (CNN) with a Deep Neural Network (DNN). Then, hierarchical DNNs are supposed to be an accident risk classifier to estimate the risk of each cell in the accident-occurrence grid. The proposed system can effectively reduce instances with no traffic accidents. Furthermore, we introduce the concept of the Accident Risk Index (ARI) to better represent the severity of risk at each cell. Also, we consider all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. To improve the prediction accuracy, we further take into consideration all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. In the experiment, we highlight the benefits of our method for urban traffic accident management by significantly improving model performance compared to the baselines. The feasibility and applicability of the proposed system are validated in the data of Daejeon City, Republic of Korea. The proposed prediction system can dynamically advise and recommend commuters, traffic management systems, and city planners on alternatives, optimizations, and interventions.

Battery energy storage systems (BESSs) play a major role as flexible energy resource (FER) in active network management (ANM) schemes by bridging gaps between non-concurrent renewable energy sources (RES)-based power generation and demand in the medium-voltage (MV) and low-voltage (LV) electricity distribution networks. However, Lithium-ion battery energy storage systems (Li-ion BESS) are prone to aging resulting in decreasing performance, particularly its reduced peak power output and capacity. BESS controllers when employed for providing technical ancillary i.e. flexibility services to distribution (e.g. through ANM) or transmission networks must be aware of changing battery characteristics due to aging. Particularly of importance is BESSs' peak power changes aiding in protection of the Li-ion BESS by restricting its operation limits of it for safety reasons and improving its lifetime in the long run. In this paper, firstly an architecture for ANM scheme is designed considering Li-ion BESSs as one of the FERs in an existing smart grid pilot (Sundom Smart Grid, SSG) in Vaasa, Finland. Further, Li-ion BESS controllers are designed to be adaptive in nature to include its aging characteristics, i.e. tracking the changing peak power as the aging parameter, when utilised for ANM operation in the power grid. Peak power capability of the Li-ion nickel‑manganese‑cobalt (NMC) chemistry-based battery cell has been calculated with the experimental data gathered from accelerated aging tests performed in the laboratory. Impact of such aging aware and adaptive Li-ion BESS controllers on the flexibility services provision for power system operators needs will be analysed by means of real-time simulation studies in an existing SSG pilot.

This study aims to understand the phase transitions, between congested and free-flow states, by estimating the congestion boundary. Since the congestion transition process occurs rapidly, the probability density distributions of traffic flow parameters, i.e. speed and density, show bimodal shapes. The congestion boundary is defined as the threshold that decomposes the bimodal distribution. The dedicated short-range communication data and toll collection system data were used to estimate congestion boundaries on the highway section from Seoul tollgate to Shingal junction. The results show that the congestion boundaries for speed, density, and flow rate were estimated to be 66.9 km/h, 22.8 veh/km, and 341.3 veh/5 min, respectively. With the flow rate at the congestion boundary, the capacity was estimated to be between 71.4% and 82.7% of traditional capacities. The congestion boundary approach provides critical thresholds for each dynamic transition phase on highways, offering crucial insights for effective congestion management.

Lithium-ion batteries are seen as a key element in reducing global greenhouse gas emissions from the transport and energy sectors. However, efforts are still needed to minimize their environmental impact. This article presents a path towards a circular economy and more sustainable batteries, thanks to their reuse in mobile charging stations for electric vehicles. This work presents the results of characterization tests and modeling of second life batteries. The presented characterization test and electrical models can be used as references to evaluate the performance of aged batteries after their first life. Detailed test procedures and data results are provided in an open-access data paper.

In series hybrid electric vehicles, the fossil energy source is composed of an electrical generator driven by an internal combustion engine. Compared to constant speed control, variable speed control of the electrical generator improves the vehicle’s energetic efficiency and releases the battery load. Such control is extremely sensitive because of the nonlinearities. In a plug-in hybrid vehicle, in addition to the obvious inherent variable speed nonlinearity, the large range of battery voltage variation increases the complexity of the controller design. Moreover, in our case, to take advantage of the variable speed feature, the generator load has transient constraints because it must follow the vehicle load. In equivalent applications, for the electrical side, usually, there is a use of high-frequency control strategies based on the generator’s three phases current and voltage acquirement. This article investigates a low-frequency power control strategy through a model-based method for a specific power electronics vehicle architecture. Starting with an adaptive proportional, integrator, and derivative (PID)-based controller to tackle the nonlinearity issues, this article explains progressively the reasons and choices that lead to design a sliding hybrid fuzzy logic controller. The designed controller demonstrates good performance in power tracking and permits to reduce fuel consumption.

What are the main factors related to road or service configuration influencing the response behaviour of connected vehicles? How does it evolve with respect to the Market Penetration Rate (MPR) of connected vehicles? Here are some questions raised by this paper with a focus made on Green Light Optimal Speed Advisory (GLOSA) strategy. Such a system, based on V2I communication, aims at providing speed advice/recommendations when approaching an intersection to adjust speed and enhance fuel consumption. The message is displayed on the Human Machine Interface (HMI) of the connected vehicles and a response is expected from the driver. This paper derives its interest in the response behaviour of the driver to HMI. It develops a two-stage methodology based on (i) Field Operational Test to collect realistic inputs (e.g., response rate, delay, deceleration profile, etc.) and (ii) a simulated environment used for extending the findings to non-observed cases (e.g. higher MPR). Besides, the methodology that is well-fitted for generic evaluation and comparison of pilots sites’ conclusions, one further contribution lies in the process to select the explaining factors. Factors are targeted among features of (i) the road configuration (e.g. number of lanes), (ii) the service configuration (e.g. activation distance), or (iii) the individual route choice and traffic conditions. Among others, it is highlighted that the activation distance plays a significant role in the response behaviour and, depending on the cycle duration, a short activation distance might be completely inefficient, while a true environmental impact requires high MPR.

End-of-life electric vehicle (EV) batteries can be reused to reduce their environmental impact and economic costs. However, the growth of the second-life market is limited by the lack of information on the characteristics and performance of these batteries. As the volume of end-of-life EVs may exceed the amount of batteries needed for stationary applications, investigating the possibility of repurposing them in mobile applications is also necessary. This article presents an experimental test that can be used to collect the data necessary to fill a battery passport. The proposed procedure can facilitate the decision-making process regarding the suitability of a battery for reuse at the end of its first life. Once the battery passport has been completed, the performance and characteristics of the battery are compared with the requirements of several mobile applications. Mobile charging stations and forklift trucks were identified as relevant applications for the reuse of high-capacity prismatic cells. Finally, a definition of the state of health (SoH) is proposed to track the suitability of the battery during use in the second-life application considering not only the energy but also the power and efficiency of the battery. This SoH shows that even taking into account accelerated ageing data, a repurposed battery can have an extended life of 11 years at 25 °C. It has also been shown that energy fade is the most limiting performance factor for the lifetime and that cell-to-cell variation should be tracked as it has been shown to have a significant impact on the battery life.

Vehicle air pollution is a significant problem for health and climate change that can be solved by several approaches. The route is one of the many components to be considered. In this work, we propose a statistical analysis of a large FCD database in November 2017 in Lyon (France) in order to find alternative sustainable trips and evaluate potential emission reductions (CO2, NOx, PM10). To this end, an innovative framework was built. First, we assessed vehicle speeds for each network section and the fifteen-minute period, when this information was reachable. Then, we used a regression random forest (RF) algorithm to fill in the missing data. This dynamical speed map allowed us to search for fewer pollutant trips, for the first ten days of November. By using COPERT emission factors (EFs) and the time-dependent Dijkstra algorithm, we successfully identified between 51% and 72% of alternative sustainable paths, depending on the engine technology and the pollutant. We investigated the influence of vehicle technology. In all cases, the number of alternative trips found tends to be the same as soon as the emission savings exceed 5%. Moreover, about 400 trips out of 11,000 have the potential to mitigate about 20% of emissions.

This paper introduces a simulation-based dynamic model for emulating the network equilibrium conditions considering path- and departure-time choices and incorporating the modelling of activities (e.g. home-work). The primary objective is to investigate the Activity-based User Equilibrium conditions for regional networks using the Macroscopic Fundamental Diagram. We analyse aggregated traffic dynamics under equilibrium conditions on a network representing the city of Innsbruck, Austria. Our study considers various settings and calibrations of the total utility of travelling. The results indicate that incorporating departure time choices and activity modelling significantly alleviates network-wide congestion, surpassing scenarios that only consider path choices for equilibrium conditions. This reduction is more evident when the network exhibits higher levels of congestion. Furthermore, we applied our model to mimic traffic dynamics under equilibrium conditions for 24 h in the entire metropolitan area of Lyon, France, using a simulation scenario calibrated with real data. Our simulation results demonstrate the versatility of the Activity-Based User Equilibrium for applications in a large-scale network, laying the groundwork for potential network-wide applications of congestion pricing or planning strategies, and developing fast simulation tools that incorporate multiple stages of the decision-making process.

Battery lifetime is an important parameter in the life cycle assessment (LCA) of a plug-in hybrid-electric vehicle (PHEV). This paper aims to study the impact of various parameters on the battery aging of a PHEV. For this purpose, model-based use cases are generated, the outputs of which are the daily driven distances for a period of one year, recharge scenarios, and battery temperature. A combined aging model (calendar and cycling aging) is used to calculate the capacity lost by the battery at the end of one year of use. The thermal model of the battery is using an electro-thermal coupling equation, for which the ambient temperature is modeled using daily minimum and maximum temperature data varying throughout the year for different cities. Finally, a sensitivity analysis is carried out using the conditioned variance method to identify the most important input parameters which largely affect the output of this study. The results of this study show that battery size, annual mileage, external temperature, and charging behavior are the most important parameters to be considered in the aging study of the battery of a PHEV personal car.

Park-and-ride systems have the potential to improve the efficiency of transportation networks by providing targeted shared mobility services. The design of a park-and-ride system depends on its role in regards to the broader transportation network. Reconfigurable park-and-ride systems aim to provide complementary shared mobility services in the context of varying travel demand scenarios, such as special events, network maintenance operations or non-recurrent perturbations. The design of reconfigurable park-and-ride systems involves the location of access and egress hubs for shared mobility services. We study an extended version of this hub location problem with integrated fleet assignment decisions. We consider stochastic scenarios representative of varying travel demand and traffic conditions on the network and propose a two-stage stochastic integer programming hub location formulation for this problem. First-stage variables represent hub location decision while second-stage variables represent both scenario-based transportation flows and fleet assignment decisions. The latter represent shared mobility service vehicles and they are modeled as integer variables. We develop solution methods to solve this two-stage stochastic integer programming hub location formulation. Exact approaches based on the L-shaped method are proposed with single- and multi-cut configurations. Valid inequalities along with a tight lower bound for the generation of optimality cuts are presented. We also develop a matheuristic to solve larger problem instances. We report numerical results on problem instances based on real data of the city of Lyon, France. We show how stochastic scenarios representative of varying demand and traffic conditions can be generated from such data. Our experiments demonstrate the benefits of this integrated modeling approach for designing efficient reconfigurable park-and-ride systems while considering fleet assignment decisions.

The interest in tradable mobility credits (TMC) is growing steadily. Compared to existing instruments, its cap-and-trade design for the demand side ensures that a limited quantity, e.g., traffic and related emissions, can by design not be exceeded. However, most TMC schemes are market-based financial instruments that can only be successful, if the market ensures the most efficient allocation of resources and if one can rely on the price. Hence, TMC schemes require trading activity and a liquid market that only emerges when participants are able and willing to trade. In this paper, we systematically review the TMC literature for aspects of trading activity and market liquidity, summarize the literature streams, and discuss determinants of participants’ ability and willingness to trade TMCs. During the literature review we separate those into demand-side, supply-side, and market regulation factors. This first coherent discussion of creating liquid TMC markets with substantial trading activity challenges the instrument and allows us to draw valuable conceptual implications for the TMC scheme design, but also implications for stakeholders beyond concept. Generating trading activity and liquid markets is thoroughly possible, but robustly achieving it can be challenging.

Continuous data streams, generated by modern sensed cities, open many opportunities and perspectives in terms of developing new innovative services. To exploit this potential, flexible and scalable platforms are needed to ease the design, development, deployment, and operations of new city services. In recent years, several problem-specific platforms have been proposed in different application domains; however, to boost the evolution of smart cities, we claim the need for city-oriented platforms that can be easily customized to address different day-to-day life challenging problems. In this paper, we present the main architectural challenges and solutions proposed for the design of a novel open-source platform (named PROMENADE) characterized by: i ) a data-driven graph-based modeling support to ensure high generality for addressing disparate problems related to the networked nature of many city infrastructures and systems, ii ) the dynamic nature of the graph entities updated in real-time from different sources ( e.g., IoT/Edge networks, data providers, etc.), and iii ) high efficiency, scalability and flexibility to easily support new city services. The platform is designed around a general-purpose core that provides a set of built-in standard features such as data ingestion , storage, processing, and visualization exposed as a collection of containerized microservices . A specialization of the platform has been developed for road networks monitoring. It has been deployed in OpenShift/Kubernetes and tested using realistic datasets collected from the city of Lyon, France. The analysis addresses an important problem of big data processing pipelines: the synchronization between data ingestion and processing in order to produce an accurate result in useful time. To this end, we study different approaches for synchronization and show how the end-to-end latency is kept under control by leveraging the scalability of the platform.

An essential element for the diffusion and environmental impact assessment of electrochemical storage systems is their lifetime. This lifetime also impacts the overall cost of the equipment in which the storage system is used. At the same time, a number of applications, e.g. electric vehicles, do not allow a temperature control of the batteries, although the performances of the latter are very strongly linked to them. The phenomena investigated, such as aging, behavior at low temperature and rapid charge for low temperature, are complex and difficult to model. Only the establishment of databases representative of the conditions of use can lead to elements of response. The exploitation of these databases by artificial intelligence tools is certainly relevant but requires a learning on data representative of the conditions of use and of the phenomena to be evaluated. The work presented in this paper is in this context and is intended to model the influence of the rapid charge at low temperature (0 °C, −10 °C, −20 °C) on the lifetime (initial capacity loss) of lithium-Ion NMC elements. The problem with data-based approaches is the large number of tests required and the development in relevant experimental designs. Faced to this challenge, a consortium of French laboratories and manufacturers has been working together since the 2000s to carry out this type of work. The paper proposes to present a test campaign and summarizes the main results to assess the service life (loss of capacity) for a fast-charging application at low temperature and position them against the manufacturer data established at 25 °C. The impact of two partial discharge processes (50 %) will also be assessed. In a last part, we show that for low temperatures, even for the nominal charge current the life time is reduced to few dozens of cycles and a mechanical destruction of the cell with no activation of the current interrupt device is achieved. This study demonstrates and quantifies the very important impact of low-temperature charging processes on the lifetime of high energy lithium-ion NMC batteries.

Experiments are essential to understand the behaviour and performance of energy storage systems. In this field, a considerable amount of experimental data is generated and data processing is a tedious task. To date, research teams working in the field of energy storage tend to focus on developing their own analysis tools rather than using existing open source software. This strategy can be detrimental to the quality and reproducibility of the research. This paper presents DATTES, a free and open source software for analysing experimental battery data. The software provides a comprehensive and customizable toolkit for extracting, analysing and visualizing experimental data. It also creates gateways to other open software and tools. In this way, DATTES enables users to get the most out of their experimental data and engage in open and reproducible science.

Urban traffic congestion remains a persistent issue for cities worldwide. Recent macroscopic models have adopted a mathematically well-defined relation between network flow and density to characterize traffic states over an urban region. Despite advances in these models, capturing the complex dynamics of urban traffic congestion requires considering the heterogeneous characteristics of trips. Classic macroscopic models, e.g., bottleneck and bathtub models and their extensions, have attempted to account for these characteristics, such as trip-length distribution and desired arrival times. However, they often make assumptions that fall short of reflecting real-world conditions. To address this, generalized bathtub models were recently proposed, introducing a new state variable to capture any distribution of remaining trip lengths. This study builds upon this work to formulate and solve the social optimum, a solution minimizing the sum of all users’ generalized (i.e., social and monetary) costs for a departure time choice model. The proposed framework can accommodate any distribution for desired arrival time and trip length, making it more adaptable to the diverse array of trip characteristics in an urban setting. In addition, the existence of the solution is proven, and the proposed solution method calculates the social optimum analytically. The numerical results show that the method is computationally efficient. The proposed methodology is validated on the real test case of Lyon North City, benchmarking with deterministic and stochastic user equilibria.

The temperature of a Lithium-ion battery was investigated, a 3D modeling approach was adopted. With the assitance of ANSYS Fluent software, the evolution of the temperature was predicted for one cell and then the work has been extended to a module of several cells. It was found for both cases, that the temperature increased when the discharge current increased. Regarding the module, the maximum temperature was achieved by the middle cells. A cooling air system was introduced into the module with different inlet velocities, and it was noticed that the temperature decreased with the increase of the velocity.

As electric mobility gains popularity, Electric Vehicles (EVs) and their batteries are becoming more attractive due to their size and energy density advantages. However, the electric grid has not undergone similar improvements, potentially impacting power stability and affecting EV energy usage and availability. The key challenge lies in managing increasing power demands from a fully EV fleet. To address this, efforts are needed to analyze the integration of EVs into the grid and optimize power distribution. In this paper, an innovative Energy Management Strategy (EMS) is proposed to effectively control energy loads, energy sources, and EVs, incorporating Vehicle-to-Grid (V2G) capability. The EMS optimizes energy flow and storage based on time of day, potential energy production, and the cost of grid electricity. The integration of this EMS results in significant benefits, with approximately 12% savings in electricity bills compared to a reference strategy.