Connected Vehicle Technology Research Articles

Adaptive policy learning for data-driven powertrain control with eco-driving

Modern powertrain control design practices rely on model-based approaches accompanied by costly calibrations in order to meet ever stringent energy use and emissions targets specified for standardized drive cycles. These practices struggle to capture the complexity and uncertainty of real-world driving. However, the deluge of operational data now available with connected vehicle technology presents opportunities to foster data-driven control design methods that adapt the powertrain control systems to their field use conditions. While the most attractive of these methods is reinforcement learning (RL), it is rarely directly applicable in physical applications due to its challenges of learning efficiency (sample complexity) and guaranteeing safety. In this paper, we propose and evaluate an adaptive policy learning (APL) framework that leverages existing source policies shipped with vehicles to accelerate initial learning while recovering the asymptotic performance of a reinforcement learning-based powertrain control agent trained from scratch. We present a critique of related residual policy learning approaches and detail our algorithmic implementations for two versions of the proposed framework. We find that the APL powertrain control agents offer in the order of 10% fuel economy improvement over a default powertrain controller of a commercial vehicle without compromising driver accommodation metrics. We demonstrate that the APL frameworks offer a viable approach towards potentially applying RL for real-world scenarios by addressing its learning efficiency issues.

A Novel Framework for Studying the Business Impact of Ransomware on Connected Vehicles

Connected vehicle technology is rapidly evolving. In the U.S. the government targets that 50% of all vehicles be electric by 2030 in order to reduce climate change. This initiative comes in the wake of an increased spate of ransomware attacks targeting transportation companies. Unlike traditional ransomware targeting computer networks, the compromise of vehicles can have disastrous consequences on businesses and ultimately the national economy as was evident in the recent Colonial pipeline attack. This research proposes a novel framework to study the spread of ransomware and its impact on connected vehicles. Our contribution is fourfold: (1) Three different ransomware infection vectors are considered for connected vehicles namely a hotspot attack, OBD dongle attack and malicious OTA updates. (2) Business impact of the ransomware is analyzed on a ride-hailing service. (3) A fog computing architecture is used to reduce latency in vehicle-to-vehicle communication and vehicle to base station communication. (4) The effectiveness of safeguard controls is studied in mitigating the ransomware spread. Our results show that ransomware can have a debilitating impact on connected vehicle businesses due to their high mobility and connectivity with attacks on average impacting earnings by 45% per hour.

A Roadside Millimeter-Wave Radar Calibration Method Based on Connected Vehicle Technology

Roadside millimeter-wave radar is one of the most important sensors in roadside perception systems, which have been widely used in intelligent traffic systems. It is important to find an effective calibration procedure for roadside radar to obtain the World Geodetic System-1984 (WGS-84) coordinates of detected targets. However, it is difficult to calibrate roadside millimeter-wave radar safely on public roads without road closures. To solve this problem, this article proposes a roadside millimeter-wave radar calibration method based on connected vehicle technology. First, all the trajectory points of vehicles detected by radar, including the connected vehicle, are collected, and the WGS-84 coordinates of the connected vehicle are obtained by vehicle-to-everything (V2X) communication with the roadside unit. Then, the trajectory points of vehicles are clustered with the density-based spatial clustering of applications with noise (DBSCAN) method, and the trajectory of the connected vehicle in the radar coordinate system is identified with the velocity-matching method automatically. The data pairs of the connected vehicle in the radar coordinate system and WGS-84 coordinate system are obtained with time synchronization. Finally, the calibration parameters are solved with five different types of optimization methods. We verify these methods on the beltway in Changsha. The results show that the improved pseudo inverse method (IPIM) and PIM achieve better performance than the extrinsic calibration method (ECM), rotate coordinate method (RCM), and improved RCM, and they can meet lane-level positioning requirements for V2X applications. This study provides an economical and effective way to solve the calibration problem for roadside millimeter-wave radar in an engineering project.

Deep learning based on connected vehicles for icing pavement detection

Slippery road conditions, such as snowy, icy or slushy pavements, are one of the major threats to road safety in winter. The U.S. Department of Transportation (USDOT) spends over 20% of its maintenance budget on pavement maintenance in winter. However, despite extensive research, it remains a challenging task to monitor pavement conditions and detect slippery roadways in real time. Most existing studies have mainly explored indirect estimates based on pavement images and weather forecasts. The emerging connected vehicle (CV) technology offers the opportunity to map slippery road conditions in real time. This study proposes a CV-based slippery detection system that uses vehicles to acquire data and implements deep learning algorithms to predict pavements' slippery conditions. The system classifies pavement conditions into three major categories: dry, snowy and icy. Different pavement conditions reflect different levels of slipperiness: dry surface corresponds to the least slippery condition, and icy surface to the most slippery condition. In practice, more attention should be paid to the detected icy and snowy pavements when driving or implementing pavement maintenance and road operation in winter. The classification algorithm adopted in this study is Long Short-Term Memory (LSTM), which is an artificial Recurrent Neural Network (RNN). The LSTM model is trained with simulated CV data in VISSIM and optimized with a Bayesian algorithm. The system can achieve 100%, 99.06% and 98.02% prediction accuracy for dry pavement, snowy pavement and icy pavement, respectively. In addition, it is observed that potential accidents can be reduced by more than 90% if CVs can adjust their driving speed and maintain a greater distance from the leading vehicle after receiving a warning signal. Simulation results indicate that the proposed slippery detection system and the information sharing function based on the CV technology and deep learning algorithm (i.e., the LSTM network implemented in this study) are expected to deliver real-time detection of slippery pavement conditions, thus significantly eliminating the potential risk of accidents.

Model for the cooperative obstacle‐avoidance of the automated vehicle swarm in a connected vehicles environment

AbstractThe obstacle‐avoidance problem of automated vehicles is a hot topic in the community of autonomous driving. The majority of the existing studies focused on the obstacle‐avoidance of a single automated vehicle. The connected vehicles technology provides the possibility of controlling a vehicle swarm to avoid the obstacle cooperatively. Through cooperation, the vehicle swarm not only can avoid an obstacle safely but also can minimize traffic delays. Therefore, this paper proposes a cooperative obstacle‐avoidance model for the automated vehicle swarm driving on the freeway based on the A2C reinforcement learning. The proposed model considers the efficiencies of both the individual and swarm in the learning, and a cooperative lane‐changing execution model is proposed to ensure that the optimal decision made by the A2C algorithm can be performed by the vehicles. Furthermore, simulations are conducted to verify the proposed model. The results indicate that the proposed model can significantly improve the overall traffic efficiency compared with the existing models. In a congested state, when the proposed model is applied to control vehicles, an optimal control range can be found (i.e. 700 m here), and within this optimal range, the traffic efficiency increases with the increment of the number of the vehicles controlled by the proposed model.

Network Design for Silent Link User Equilibrium

Connected vehicles (CVs) are anticipated to improve road safety and travel efficiency in a transportation system. However, the deployment of CV technologies in transportation networks can lead to privacy issues, as the communication among CVs can expose vehicles' location information. To address this issue, we introduce a privacy protection method named "silent link" to transportation networks and propose a silent link user equilibrium (SLUE) framework to study the impact of privacy protection countermeasures on network flow. A theoretical analysis regarding existence and uniqueness conditions of SLUE is provided. The proposed SLUE facilitates privacy-oriented network design to achieve optimal levels of privacy for CVs. Accordingly, a bi-level network optimization problem is formulated for the design of silent links in transportation networks. Numerical examples are demonstrated using the Braess and Sioux Falls networks.

Internet-of-Things (IoT) Platform for Road Energy Efficiency Monitoring

The road transportation sector is a dominant and growing energy consumer. Although investigations to quantify the road infrastructure's impact on energy consumption have been carried out, there are currently no standard methods to measure or label the energy efficiency of road networks. Consequently, road agencies and operators are limited to restricted types of data when managing the road network. Moreover, initiatives meant to reduce energy consumption cannot be measured and quantified. This work is, therefore, motivated by the desire to provide road agencies with a road energy efficiency monitoring concept that can provide frequent measurements over large areas across all weather conditions. The proposed system is based on measurements from in-vehicle sensors. The measurements are collected onboard with an Internet-of-Things (IoT) device, then transmitted periodically before being processed, normalized, and saved in a database. The normalization procedure involves modeling the vehicle's primary driving resistances in the driving direction. It is hypothesized that the energy remaining after normalization holds information about wind conditions, vehicle-related inefficiencies, and the physical condition of the road. The new method was first validated utilizing a limited dataset of vehicles driving at a constant speed on a short highway section. Next, the method was applied to data obtained from ten nominally identical electric cars driven over highways and urban roads. The normalized energy was compared with road roughness measurements collected by a standard road profilometer. The average measured energy consumption was 1.55 Wh per 10 m. The average normalized energy consumption was 0.13 and 0.37 Wh per 10 m for highways and urban roads, respectively. A correlation analysis showed that normalized energy consumption was positively correlated to road roughness. The average Pearson correlation coefficient was 0.88 for aggregated data and 0.32 and 0.39 for 1000-m road sections on highways and urban roads, respectively. An increase in IRI of 1 m/km resulted in a 3.4% increase in normalized energy consumption. The results show that the normalized energy holds information about the road roughness. Thus, considering the emergence of connected vehicle technologies, the method seems promising and can potentially be used as a platform for future large-scale road energy efficiency monitoring.

Assessing the Impact of Safety Countermeasures on Dilemma Zones at Signalized Intersections of Urban Roads: a Driving Simulator Study

When drivers approach a signalized intersection at the start of the yellow signal, they might be reluctant to decide whether to stop or go through the intersection due to the dilemma zone (DZ), with the consequent risk of improper behaviors that can lead to rear-end collisions and right-angle crashes. The main goal of this research is to analyze the driver's behavior at the onset of the yellow signal and to identify the most effective countermeasures for the resolution of the dilemma zone in order to improve the safety and efficiency of urban signalized intersections. A driving simulator study was carried out, and three different countermeasures were specifically designed and tested: Green Signal Countdown Timers (GSCT) (C1); a new scheme of vertical and horizontal warning signs (C2); and an in-vehicle advanced driving assistance system that uses Augmented Reality (AR) and connected vehicle technologies (C3). Forty-six volunteers took part in the experiments, driving the same scenario four times (three with countermeasures and one as a baseline condition). The results demonstrated that with countermeasure C1, the length of the DZ increased with respect to the baseline condition; moreover, the stop/go drivers’ decisions were found to be more inconsistent, increasing the potential risk of rear-end crashes. Conversely, countermeasures C2 and C3 resulted in a reduction of DZ length (-30.5% and 21.6%, respectively); in addition, C2 was found to be the one that recorded the greatest consistency of drivers’ decision-making behaviors, while C3 provided the drivers with timely and personalized early-stop warnings and recorded fewer wrong behaviors. Based on the results of this study, C2 and C3 countermeasures might be a good way to improve safety and operations at urban signalized intersections and cut down on the number of drivers who aren't sure what to do when the yellow light comes on.

Application of Information-Sharing for Resilient and Sustainable Food Delivery in Last-Mile Logistics

The growing food demand, the tendency for organic food, and the adaptation of the e-commerce business model require new food supply chain management approaches. On the one hand, 30% of the world’s produced food is wasted, and CO2 emissions are rapidly growing due to transport. On the other hand, the increasingly complex and dynamic environment is decreasing the effectiveness of food supply chains. Because of these trends, sustainability and resilience are becoming more relevant to food supply chains. Therefore, the objective of this paper is to propose a strategy based on information exchange to improve food quality and decrease the level of CO2 emission in last-mile deliveries of food products. To achieve this goal, an agent-based model of last-mile deliveries was developed. The model simulated traffic flow and traffic accidents as disturbances in the system while measuring the level of CO2 emission and food quality of the network. The simulation compares information sharing between all vehicles in the urban area and without information sharing in four scenarios of the food industry. In practice, information sharing is achieved by using connected vehicle technology. The use of information sharing between vehicles in last-mile delivery processes allows the development of a self-organizing system, which would adapt to disturbances and lead to the development of sustainability in the long run.

Simulation Study of Passing Drivers’ Responses to the Autonomous Truck-Mounted Attenuator System in Road Maintenance

The autonomous truck-mounted attenuator (ATMA) system is a lead–follower vehicle system based on autonomous driving and connected vehicle technologies. The lead truck performs maintenance tasks on the road, and the unmanned follower truck alerts passing vehicles about the moving work zone and protects workers and the equipment. While the ATMA has been under testing by transportation maintenance and operations agencies recently, a simulator-based testing capability is a supplement, especially if human subjects are involved. This paper aims to discover how passing drivers perceive, understand, and react to the ATMA system in road maintenance. With the driving simulator developed for this ATMA study, the paper performed a simulation study wherein a screen-based eye tracker collected 16 subjects’ gaze points and pupil diameters. Data analysis evidenced the change in subjects’ visual attention patterns while passing the ATMA. On average, the ATMA starts to attract subjects’ attention from 500 ft behind the follower truck. Most (87.50%) understood the follower truck’s protection purpose, and many (60%) reasoned the association between the two trucks. Nevertheless, nearly half of the participants (43.75%) did not recognize that the ATMA is a connected autonomous vehicle system. While all subjects safely changed lanes and attempted to pass the slow-moving ATMA, their inadequate understanding of the ATMA is a potential risk, for issues such as cutting into the ATMA. The results implied that transportation maintenance and operations agencies should consider this in establishing the deployment guidance.

Evaluating the Effectiveness of Countermeasures in Improving the Safety of Highway Merging Zones

The merging process from an acceleration lane to the through lane of a motorway is an important aspect at interchanges, both in terms of safety and operating conditions. Several studies have demonstrated that the merging zones of interchanges are the main sources of interference between through and entering vehicles. In this context, incorrectly assessed gaps and headways can lead to severe crashes and traffic delays at interchanges. This study investigates the effectiveness of different countermeasures to improve the safety of merging zones and the ability of through drivers to adopt safe headways to vehicles entering from the motorway on-ramp. Four different countermeasures were tested in a driving simulator study: i) a gap metering signalization, consisting of a Variable Message Sign (VMS) and new pavement markings; ii) a static symbol projected on the vehicle's windshield by means of a Head-Up Display (HUD) that informed the driver to maintain safe headways to the entering vehicle; iii) a dynamic symbol based on Augmented Reality (AR) technology, built into connected vehicle technology, that provided additional visual information to the driver about his current headway to the entering vehicle; iv) the AR system was also tested with an additional audio warning. The driving behavior of forty-four drivers under the four different configurations based on the tested countermeasures was then compared to the driving behavior recorded under a configuration without any countermeasures (baseline condition). The results revealed significant positive effects of all the countermeasures, especially of the AR systems that helped through drivers to adjust their headway to the entering vehicle and thus the most effective solution for improving the safety of the merging zone. This study confirmed the great potential of AR and connected vehicle technologies to improve general safety conditions on the road network, especially in risky situations and difficult maneuvers.

Switching Strategy for Connected Vehicles Under Variant Harsh Weather Conditions

With the development of 5G networks and advanced communication technologies, connected vehicles (CV) are becoming an increasingly important aspect of the future of transportation. The connected vehicles will usually generate a large amount of data that require fast and reliable communication channels with low latency. 5G millimeter-wave (mmWave) is crucial for the next generation of vehicle-to-vehicle (V2V) communications in CV scenarios. However, harsh weather conditions such as rain, snow, dust, and sand can significantly impact the performance of 5G mmWave channels for V2V communications. Maintaining seamless connections for connected vehicles during harsh weather conditions is a significant challenge that researchers must address. In this paper, we propose a two-stage strategy enabling connected vehicles to operate effectively under moderate and severe weather conditions. Our proposed approach involves a prediction step, which uses machine learning techniques to forecast weather patterns and determine the optimal communication strategy, followed by a switching step, which seamlessly chooses between frequency or channel switch based on the prediction. By incorporating these two steps, we aim to provide a robust and efficient communication system that can adapt to different weather conditions. The NS3 simulation results show that our switching strategy is effective and can benefit the field of connected vehicle technology.

Physics-Aware Learning-Based Vehicle Trajectory Prediction of Congested Traffic in a Connected Vehicle Environment

The physics of shockwaves is a fundamental traffic characteristic that is useful for microscopic traffic flow modeling. Thanks to connected vehicle technologies, it is possible to capture shockwaves by collecting the information of multiple downstream vehicles. Numerous classical physics-based models have utilized the physics of shockwaves to predict vehicle trajectory dynamics, yet their predictability is often limited due to the volatile and complex nature of highway traffic composed of human-driven vehicles. Recent learning-based trajectory prediction models utilize historical trajectories of surrounding vehicles to improve predictability. However, those learning-based models are purely data-driven, thus lacking interpretability and physical insights, or even missing opportunities for further improving model predictability. To leverage the advantages of both learning-based and physics-based models, this study proposes a physics-aware learning-based model for a trajectory prediction of congested traffic in a connected vehicle environment. A newly collected highway trajectory dataset is adopted for training and validation. Experiment results show that the proposed hybrid model yields better predictability, compared with the learning-based models (e.g., long short-term memory neural networks and convolutional neural networks), with an 8.7% predictability reduction of position errors and a 6.5% reduction of speed errors, which further verify the positive impacts of adopting physics of shockwaves in hybrid learning models. Moreover, result analysis shows that predictability improves as the market penetration rate increases, and the proposed hybrid model is better than the learning-based models with 3-10% improvements in predictability.

Intention to perform eco-driving and acceptance of eco-driving system

Eco-driving is one strategy for reducing transportation sector fuel usage and greenhouse gas emissions. With the advancement of connected-vehicle technology, the dynamic eco-driving concept can utilize real-time vehicle-specific information to optimize vehicle speed, thereby further reducing fuel consumption and emissions. The objective of this research was to determine the elements that influence drivers' intentions to practice eco-driving and their acceptance of eco-driving technology. A theoretical model of technology acceptance for both internal combustion engine vehicle (ICEV) and electric vehicle (EV) drivers was built using a mix of the Theory of Planned Behavior (TPB), the Technology Acceptance Model (TAM), and Goal Framing. Drivers’ acceptance of eco-driving system was hypothesized to be based on their intention to perform eco-driving. The model's validity was verified using a structural equation modeling analysis of data from a survey with 340 replies from ICEV drivers and 315 responses from EV drivers. The findings corroborated the original hypotheses in TAM and TPB, and drivers' intention to practice eco-driving had an indirect effect on their intention to utilize the system via the construct of perceived ease of use. In comparison to ICEV drivers, EV drivers possessed a greater understanding of eco-driving. The four goal framing structures each played a different role in the ICEV and EV models. In the ICEV model, the altruistic goal contributed positively to the social norm construct. By contrast, the social norm was positively influenced by the biospheric and the egoistic goals, and negatively influenced by the hedonic goal in the EV model. This study's framework and results provide theoretical and practical guidelines for researchers, manufacturers, and policy-makers to understand drivers' motivation to perform eco-driving and increase drivers' acceptance of the eco-driving system.

Predicting intersection crash frequency using connected vehicle data: A framework for geographical random forest

Accurate crash frequency prediction is critical for proactive safety management. The emerging connected vehicles technology provides us with a wealth of vehicular motion data, which enables a better connection between crash frequency and driving behaviors. However, appropriately dealing with the spatial dependence of crash frequency and multitudinous driving features has been a difficult but critical challenge in the prediction process. To this end, this study aims to investigate a new Artificial Intelligence technique called Geographical Random Forest (GRF) that can address spatial heterogeneity and retain all potential predictors. By harnessing more than 2.2 billion high-resolution connected vehicle Basic Safety Message (BSM) observations from the Safety Pilot Model Deployment in Ann Arbor, MI, 30 indicators of driving volatility are extracted, including speed, longitudinal and lateral acceleration, and yaw rate. The developed GRF was implemented to predict rear-end crash frequency at intersections. The results show that: 1) rear-end crashes are more likely to happen at intersections connecting minor roads compared to major roads; 2) a higher number of hard acceleration and deceleration events beyond two standard deviations in the longitudinal direction is a leading indicator of rear-end crashes; 3) the optimal GRF significantly outperforms Global Random Forest, with a 9% lower test error and a substantially better fit; and 4) geographical visualization of variable importance highlights the presence of spatial non-stationarity. The proposed framework can proactively identify at-risk intersections and alert drivers when leading indicators of driving volatility tend to worsen.

Dynamic traffic-aware auction-based signal control under vehicle to infrastructure communication

The advent of connected vehicle technology brings forth a new set of possibilities for more efficient traffic control. Indeed, the ability to consider driver-specific attributes, such as value of time or willingness to pay, in intersection management through advanced communication protocols allows for reducing individual delay costs. In this context, this study presents an auction-based approach for signalized intersection control under a connected vehicle setting. A second-price sealed-bid auction is employed to assign green time to conflicting movements, while driver bids and bidding distance per lane vary based on delay accumulation. The proposed auction-based control is evaluated using various demand levels and flow patterns and compared against pre-timed signal control. Results show that the proposed mechanism may be a promising alternative for several flow patterns, achieving lower average delays while maintaining fairness.

An In-Vehicle Warning Information Provision Strategy for V2V-Based Proactive Traffic Safety Management

The availability of vehicle interaction data, which is obtained by an in-vehicle forward collision warning system, including spacing between the leading and the following vehicle and time-to-collision, provides a valuable opportunity to predict crash risks in real time. When this opportunity is combined with connected vehicle technologies including vehicle-to-vehicle wireless communications, it is expected that more effective crash prevention would be achievable by providing predictive warning information as a part of proactive traffic safety management (PTSM). The purpose of this study is to develop a more reliable in-vehicle warning information provision strategy based on the prediction of crash risks using vehicle interaction data. A crash risk prediction model based on a long short-term memory was able to predict the crash risk after 3 seconds with a mean absolute percentage error of 8% using the data for the past 5 seconds. The predicted crash risk data were applied to derive the optimal threshold for triggering in-vehicle warning information, which is the essence of the proposed warning provision strategy. This study defined three indicators to evaluate the reliability of warning information: correct detection rate (CDR), detection failure rate (DFR), and information provision rate (IPR). An exemplar analysis result showed that the optimal threshold to minimize IPR in a situation where CDR and DFR are 100% and 0%, respectively, was identified as 0.69. The proposed methodology that predicts crash risks in real time and provides V2V-based warning information in a more proactive manner is expected to mitigate the crash risk significantly.

Security Issues and Solutions for Connected and Autonomous Vehicles in a Sustainable City: A Survey

Connected and Autonomous Vehicles (CAVs) combine technologies of autonomous vehicles (AVs) and connected vehicles (CVs) to develop quicker, more reliable, and safer traffic. Artificial Intelligence (AI)-based CAV solutions play significant roles in sustainable cities. The convergence imposes stringent security requirements for CAV safety and reliability. In practice, vehicles are developed with increased automation and connectivity. Increased automation increases the reliance on the sensor-based technologies and decreases the reliance on the driver; increased connectivity increases the exposures of vehicles’ vulnerability and increases the risk for an adversary to implement a cyber-attack. Much work has been dedicated to identifying the security vulnerabilities and recommending mitigation techniques associated with different sensors, controllers, and connection mechanisms, respectively. However, there is an absence of comprehensive and in-depth studies to identify how the cyber-attacks exploit the vehicles’ vulnerabilities to negatively impact the performance and operations of CAVs. In this survey, we set out to thoroughly review the security issues introduced by AV and CV technologies, analyze how the cyber-attacks impact the performance of CAVs, and summarize the solutions correspondingly. The impact of cyber-attacks on the performance of CAVs is elaborated from both viewpoints of intra-vehicle systems and inter-vehicle systems. We pointed out that securing the perception and operations of CAVs would be the top requirement to enable CAVs to be applied safely and reliably in practice. Additionally, we suggested to utilize cloud and new AI methods to defend against smart cyber-attacks on CAVs.

An eco-driving algorithm based on vehicle to infrastructure (V2I) communications for signalized intersections

Efficient operations of traffic signals are of critical importance in urban areas, as signalized intersections prevent the smooth flow of traffic and cause delays. This paper devises an eco-driving algorithm based on connected vehicle technologies, with basic kinematic wave and car-following models. The objectives of the proposed algorithm are to increase the throughput of signal intersections and decrease fuel consumption. Specifically, we focus on a signalized intersection under mixed traffic flows with connected and autonomous vehicles (AVs) and human-driven vehicles (HVs). Through the proposed algorithm, the vehicle speeds at the intersection (i.e., the intersection control speed) and signal timings can be adjusted in response to the real-time traffic conditions. According to the signal timing and the speed at the intersection, the algorithm estimates the time points of each vehicle entering the intersection. An advisory speed limit approach is formulated for each AV, making the vehicle enter the intersection at the allocated timing with the control speed. An onboard alert is set for each HV to stop or pass through. The algorithm is evaluated under various market penetration rates of AVs, different congestion levels, and with signal actuation. The results indicate that the eco-driving algorithm can increase the throughput and average travel speed at signalized intersections in addition to gaining fuel savings.

Online mixed-integer optimal energy management strategy for connected hybrid electric vehicles

In this paper, an online mixed-integer optimal energy management strategy is proposed for connected hybrid electric vehicles. Firstly, a predictive framework is constructed based on the backpropagation neural network, aiming to predict the future information utilizing the connected vehicle technology. Subsequently, for the mixed-integer programming problem in the predictive horizon, a novel optimal algorithm is proposed in the predictive framework. Finally, the proposed strategy is verified under both simulation and hardware-in-the-loop system environments. The results show that the proposed strategy reduces fuel consumption by 25.34% and 1.13% compared with the rule-based EMS and equivalent consumption minimization strategy (ECMS)-based EMS, and reduces fuel consumption by 25.79% and 1.78% compared with the rule-based EMS and ECMS-based EMS in two typical conditions. The proposed strategy can reduce 84% computation time than the particle swarm optimization-based EMS in the same typical condition. Using real-word conditions, the proposed strategy can reduce fuel consumption by 9.2% compared with ECMS-based EMS. The proposed strategy achieved satisfactory results in a hard-in-loop experiment.